Machine learning
296 notes, newest first. Includes the vault tags machine learning, ml, machine learning models, deep learning, neural networks.
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
WikiSkill is a framework that helps AI agents evolve their skills by creating a persistent knowledge base (wiki) to store and consolidate their experiences. This framework outperforms other skill-evolution methods…
An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction
The study presents a three-step approach for integrating data collection, processing, and predictive modeling in travel behavior research using conversational surveys, machine learning, and large language models…
An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction
This research proposes a three-step workflow integrating chatbot-administered surveys, data processing, and behavioral prediction for travel behavior modeling and weather-sensitive demand forecasting. The study uses…
Catching the Rug: Early Prediction of Fraudulent Memecoins on Solana via Machine Learning
This research focuses on predicting rug pulls, a form of fraud in memecoins traded on the Solana blockchain, using machine learning models. The study assembles a dataset of over 6 million tokens traded over 7 months…
Electronic Navigational Chart Change Classification
The authors propose an automated method to classify changes in Electronic Navigational Charts (ENCs), which are used in maritime navigation systems. The proposed approach involves encoding complex vector data changes…
EnvHarness: Awakening Static Worlds for Agent Learning
The paper proposes a new system called Environment Harness (EnvHarness) to improve static environments used in learning by AI agents. The system can adapt the behavior of these environments without modifying their…
MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
The paper presents MaliciousSkillBench, a comprehensive benchmark for detecting malicious Agent Skills in large language models (LLMs). The benchmark consolidates various sources of malicious artifacts and reduces them…
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use
Researchers have introduced a new benchmark called MemTrapBench to test the performance of large language models (LLMs) in terms of cognitive traps caused by their memory components. The study identifies two types of…
Repo0: Design-Driven Zero-to-All Code Generation
The paper introduces Repo0, a framework for zero-to-all code generation that maintains an explicit architectural state using a Dual-Directed Acyclic Graph (Dual-DAG). It iteratively evolves component boundaries guided…
Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection
The paper presents Task-CoEvolve, a new approach to optimize language model agent harnesses efficiently by adaptively selecting validation tasks. It addresses the challenge of using fixed validation sets by co-evolving…
Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection
Researchers have developed a method called Task-CoEvolve to improve the efficiency of harness optimization for large language models (LLMs). This method co-evolves validation tasks with the harness by focusing on tasks…
Beyond the Transcript: Detecting Covert Co ordination in Latent Multi-Agent Communication
Researchers have developed Verifiable Latent Alignments (VLA), a framework for monitoring and controlling communication between language-model agents that occurs through hidden states not visible in public transcripts…
Finetuning Strategies for Querying Sounds by Vocal Imitation
The authors describe their winning strategy for a sound effect querying competition in 2025, which involved two fine-tuning strategies: contrastive learning with a frozen pretrained CED encoder and joint…
Grouping the Stochastic Machine: Precision, Not Capability, as the Frontier Metric for AI Systems
The author argues that precision, rather than capability, should be the focus when comparing and measuring AI systems. Precision refers to how consistently an AI system performs the same task, while capability is where…
Harness Continual Learning: Continual Adaptation Beyond Model Parameters
The paper presents a new paradigm for continual learning called Harness Continual Learning (HCL). In this approach, an agent can adapt through a harness of prompts, memories, tools, skills, and routing rules. The…
Interpretable AI predicts a 2026 summer dry anomaly in central China
Researchers have developed an AI model that predicts a dry anomaly in central China during the summer of 2026. This prediction is based on atmospheric circulation patterns, particularly a persistent cyclonic…
Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots
Researchers developed a method called EvalCEGAR to automatically create an evaluation metric for AI agents in tasks like report generation, where traditional metrics are difficult to develop. The method involves…
Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets
The authors propose a method to utilize multiple Intel AI PCs with integrated GPUs and NPUs, even when they have insufficient memory for large models like a 70B-parameter LLM. The method involves breaking the model…
Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
The paper investigates the performance of large language models (LLMs) in extracting contextualized information from research articles, finding that while LLMs can perform well with expert-curated prompts, they may…
Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models
The paper presents EvoResearcher, a training-free protocol for adding cost-bounded self-reflection to large language models (LLMs). The protocol is designed to work with a single frozen LLM backbone and aims to improve…
AutoSR: Automatic Symbolic Regression by Searching Research States
The authors introduce AutoSR, a fully automated system that searches for persistent scientific investigations instead of isolated equations in symbolic regression. Unlike traditional methods, AutoSR preserves the…
Orbit-Planner: Towards Latent World Models for On-Orbit Obstacle Avoidance of Satellite Agents
The paper presents Orbit-Planner, a system designed to help satellite agents navigate in space by predicting collision risks with limited onboard observations. It introduces a two-stage latent world model for on-orbit…
UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures
Researchers propose UniTAC, a universal image compression system for physical AI systems like autonomous vehicles and robots. The system can adapt to changing tasks without retraining, using task-specific importance…
Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams
A new benchmark called Diagram-MMU has been created to test the ability of Multimodal Large Language Models (MLLMs) in parsing and understanding scientific diagrams. The benchmark includes 3,700 curated diagrams and…
Redistribution-based Cost Inference Improves Sparse Safe Offline RL
A new framework called Redistribution-based Cost Inference (RCI) is proposed to convert sparse stop-feedback in safe offline reinforcement learning into dense per-step costs. This conversion helps train a constrained…
Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection
Researchers present BENCH2ROBUST, a framework for converting reliable tool-use benchmarks into stochastic environments with controlled solvability. This allows study of agent's response to tool failures, which can be…
VICBench: A Multi-Language Benchmark for Code Vulnerability Detection
Researchers have created a benchmark dataset called VICBench for evaluating code vulnerability detection tools. The dataset contains 100 verified vulnerabilities across 88 projects in Python, Java, and C++, covering 48…
GitSkills: A Dataset of Agent Skills on GitHub
The paper introduces GitSkills, a dataset of 3,797,117 SKILL.md files collected from public GitHub repositories in July 2026. The dataset retains every file occurrence with its repository, path, and content hash. It…
Hypothesis Frontier: Verifier Guided LLM and Symbolic Search for First-Order Induction
The paper introduces Hypothesis Frontier, a framework that uses a combination of language models (LLMs) and symbolic processing to solve first-order concept synthesis problems. The system iteratively generates and…
SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation
Researchers introduce Visual Skill Cards (VSCs), a new method for improving the decision-making abilities of computer agents in GUI environments. VSCs are memory representations that bind reusable procedures with…
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
SkillZip is an evaluation-free method that helps compress skills by identifying their shortest faithful structural explanations, making it easier to reuse common action sequences without needing to repeat them. This…
Two-stage Odd Residual Flows for Mean-Preserving Probabilistic Time Series Forecasting
Researchers propose a new method called Two-stage Odd Residual Flows (TORF) for probabilistic time series forecasting. The method aims to address the trade-off between distributional flexibility and accurate mean…
V-FiLLM: Verified Financial LLM Reasoning Benchmark
Researchers have created a new framework called V-FiLLM to evaluate the abilities of Language Models (LLMs) in financial reasoning using structured data. The framework generates questions from executable computation…
Whisper-Aware LLM: Self-Supervised Uncertainty Learning for Robust Whispered Speech Recognition
The Whisper-Aware LLM is a new framework designed to improve the performance of ASR (Automatic Speech Recognition) systems for whispered speech. The model learns to perceive and react to the uncertainty associated with…
Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding
The paper discusses the growth of Agentic coding README files like CLAUDE.md in real repositories and attributes this to imperfect recall. The authors refer to this phenomenon as 'catastrophic remembering'. They find…
Agentic Auto-Research is Fuzz Testing
The authors argue that current methods for autonomous research agents are inefficient due to the slow validation process of generated experiments. They propose to adapt fuzzer techniques, which use feedback from…
ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization
The paper presents ElasticBack, a stealthy conditional backdoor that can compromise LLM agents by planting a rule and trigger in skills. The backdoor only activates when both the rule and the trigger appear together…
Multimodal Model Diffing for Feature Discovery and Control
Researchers developed a framework called MMDiff to help understand, control, and audit the behavior of Multimodal Large Language Models (MLLMs). The framework identifies features that are altered by multimodal…
NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation
The study introduces a new method called NeuroRefiner for accurately segmenting neurons in 3D fluorescence microscopy images. The method overcomes challenges posed by the sparse and elongated morphology of neurons…
Rethinking Factor Sharing in Federated LoRA: A Rank-Aware Adaptive Approach
Researchers propose a new method for fine-tuning large language models in a federated learning paradigm using Low-rank adaptation (LoRA). They investigate two strategies, Share-A/Local-B and Share-B/Local-A, and reveal…
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
A research paper proposes a new method for document search called Reliable Embedding-free Agentic Document-search (READ), which is designed to overcome limitations in current methods for long documents, particularly…
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
The authors propose a new method for document search called READ (Reliable Embedding-free Agentic Document-search). This method uses an interpretable agent that performs three operations: normalized lexical search…
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
The paper proposes a new approach for document search called 'READ (Reliable Embedding-free Agentic Document-search)', which aims to address the issues with current black-box retrieval designs in handling long…
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
The authors propose a new method for document search called Reliable Embedding-free Agentic Document-search (READ). In contrast to the common design of retrieval-augmented generation, READ uses an agent that reads the…
Challenges in Evaluating Explanation Methods for Static and Evolving Data
The paper discusses the limitations in evaluating Explainable Artificial Intelligence (XAI) systems, specifically focusing on the DetoxAI image recognition system. It highlights the need for better evaluation methods…
Comparative Approaches to Agent Retrieval over Large Skill Libraries
The study compares two systems for deciding which skills to load from a large skill library by an agent. The first system is a hybrid ranker that combines lexical and dense-embedding retrieval, while the second system…
Comparative Approaches to Agent Retrieval over Large Skill Libraries
The study compares two systems for deciding which skills to load from large skill libraries in AI agents. The first system is a hybrid ranker that combines lexical and dense-embedding retrieval for sparse, on-demand…
Comparative Approaches to Agent Retrieval over Large Skill Libraries
The research compares two systems for deciding which skills to load from a large skill library when creating agents. One system combines lexical and dense-embedding retrieval, while the other uses a typed knowledge…
Comparative Approaches to Agent Retrieval over Large Skill Libraries
Researchers compared two methods for deciding which skills to load from large skill libraries in AI agents: a hybrid ranker combining lexical and dense-embedding retrieval, and a typed knowledge graph encoding workflow…
Contextual Information Policy Optimization for Search Agents
The text introduces a new method called Contextual Information Policy Optimization (CIPO), which aims to improve the reliability of search agents by ensuring they use retrieved evidence effectively during multi-step…
Contextual Information Policy Optimization for Search Agents
The researchers propose a new reinforcement learning framework called Contextual Information Policy Optimization (CIPO) to improve the reliability of search agents for knowledge-intensive tasks. CIPO encourages the use…
Does FLAIR super-resolution erase or hallucinate small white-matter lesions?
The study investigates whether using super-resolution (SR) techniques on Fluid-attenuated Inversion Recovery (FLAIR) scans affects the detection of small white-matter lesions. The research finds that SR tends to erase…
FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
The research introduces a new benchmark called FinEvo-Bench for evaluating the performance of self-evolving agents in professional financial workflows. The benchmark consists of 120 real-case-grounded tasks across six…
From Passive Mirrors to Active Agents: Holonic Digital Twins for Physical AI over Networks
The paper proposes a framework called Holonic Digital Twins Networks (HDT-Nets) to improve the performance of AI in physical systems like robots and vehicles. The framework aims to deliver real-time physical AI…
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
Researchers have introduced HarnessOpt-Bench, a benchmark to measure the performance of Large Language Models (LLMs) in optimizing their own harnesses (the prompts, tools, etc. surrounding them). The research shows…
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
The paper introduces HarnessOpt-Bench, a benchmark for evaluating the ability of Language Models (LLMs) to optimize the harnesses surrounding them, which includes prompts, tools, control flow, memory, and orchestration…
iARCS: Iterative Agentic RL for Controllable 3D Scene Generation
The paper presents iARCS, an iterative agentic reinforcement learning framework for enhancing the performance of synthetic 3D scene generators by adapting them to meet task-specific functional constraints, such as…
QuanTiMedAI: Quantum-Enhanced Time-Series Model guided by Agentic AI for Cardiac Arrest Mortality Prediction
The researchers introduce QuanTiMedAI, a framework for predicting cardiac arrest mortality using agentic AI and quantum enhancement in time series models. The system combines an agentic large language model for…
Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data
Researchers have developed a system called TYTAN that can automatically construct an analytic semantic schema from a relational database, helping to reduce the need for manual knowledge acquisition and potentially…
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
Researchers have developed a new framework called A-SR for symbolic regression. This framework uses a self-evolving agentic system that shifts control from expression edits to role-conditioned evidence views. It…
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
A research paper introduces a new framework called A-SR for symbolic regression. A-SR is designed to discover closed-form equations from data and uses a self-evolving agentic system that coordinates formula discovery…
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
Researchers propose Observation-Calibrated Self-Distillation (OCSD) to address a confounding issue in On-Policy Self-Distillation (OPSD), a method used to train large language model agents. OCSD aims to attribute…
Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
The paper introduces CoCoEvolve, a method aimed at improving the consistency between chart, table, and code representations in AI systems. The method optimizes models based on agreement between different…
From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking
The paper presents an auditable information harness that combines dynamic Poisson-family models and large language models (LLMs) to forecast football scores. The system goes through four iterations, each improving on…
InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval
The paper proposes a new method called InsightEmb for learning action-intent embeddings to improve agentic insight retrieval, which helps self-improving agents make better decisions by using insights from prior…
MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation
In the paper 'MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation', the authors propose a new approach for training wireless foundation models. Instead of pre-training on channel tensors…
NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critical Scenario Assessment
Researchers propose NSF-HRPT, a framework that uses a Neural Semantic Field (NSF) to model scene semantics, trajectory predictions, and probabilistic Time-to-Collision (TTC) distributions from simulation data. During…
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
The research presents a new approach called OctoLong for creating longer contexts for language models. It uses an AST parser, a language server backend, and a package manager to retrieve code references from various…
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
In this research, a new pipeline called OctoLong is introduced to enhance the training of language models (LM) by providing them with long code contexts. This is done through the use of an AST parser, a language server…
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
The paper introduces a new method called On-Policy Self-Distillation with Visual Modality Balance (OPD-V) to improve the visual reasoning of multimodal large language models. The authors argue that previous methods…
CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance
Researchers introduce CACHE-UK, a framework designed for efficiency and accuracy in deploying large language models (LLMs) in the dynamic field of finance. The system addresses the 'quantization stability crisis' that…
One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence
The paper presents a study on auditing multiple Language Learning Models (LLMs) with limited budgets, where human auditors have to evaluate self-reported confidence that may be miscalibrated and correlated. The…
ORCA-bench: How Ready Are Language Model Agents for Oncall?
The paper introduces ORCA-bench, a benchmark for testing the performance of large language models in oncall root cause analysis (RCA). The benchmark includes a live microservice system with six days of metrics, logs…
ORCA-bench: How Ready Are Language Model Agents for Oncall?
The study presents ORCA-bench, a benchmark for evaluating the performance of large language models in oncall root cause analysis (RCA). The benchmark exposes a microservice system with six days of data and 1,079 RCA…
WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning
Researchers introduce WIDE, a dynamic token-level pruning framework for improving the efficiency of large language models (LLMs). The framework allows each token to select attention and FFN channel groups dynamically…
A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Communities
Researchers studied whether AI agents comply with contribution rules in open-source communities. They found that the AI agents do not proactively retrieve the rules but improve with reminders, quotes, or feedback…
A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Communities
The study investigates whether AI-generated code in open-source communities complies with the established contribution rules. The researchers find that current AI models rarely read or follow the rules on their own…
Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility
Researchers have developed a new method for controlling large language models during scientific discovery tasks. The method, called CostAda, takes into account the costs associated with each action in addition to the…
CoCaRS: Correlation Calibration-Based Redundancy Suppression for Heterogeneous Knowledge Distillation
The research introduces Correlation Calibration-based Redundancy Suppression (CoCaRS), a method for knowledge distillation in heterogeneous settings where teacher and student models have different architectures. The…
DLAM: Distributional Latent Actions with Temporal Constraints
The paper introduces DLAM, a distributional latent-action model that aims to overcome the limitations of existing models by representing each transition as a diagonal Gaussian. This model is designed to learn more…
From Passive Video to Editable Experience: Physically Grounded Experience Synthesis for Embodied Intelligence
Jia Luo introduces Pegasus, a framework to help robots learn from human manipulation videos by translating the human demonstrations into data that can be understood by robots. The method involves creating an…
Improving Item Discoverability in e-Commerce Search via Related Intent Generation
The researchers present a scalable system called 'discovery-augmented search' that aims to improve the discoverability of items in e-commerce marketplaces, particularly grocery. This system uses intent-conditioned…
Multimodal fusion of visual and morphometric features for avian bone classification
Researchers developed a framework that combines convolutional neural network-based image analysis with standardized morphometric data for classifying bird bones. The model achieved 86% accuracy in identifying skeletal…
SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context
Researchers propose SciFigQual-Bench, a benchmark for evaluating the quality of scientific figures in computer science papers across five dimensions. The dataset includes over 6,000 images from top conferences between…
Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents
The paper presents a new approach, Cost-Aware Marginal Decision-Focused Stopping (CAM-DF), for tool selection in Large Language Model (LLM) agents that use various external services. The approach addresses the…
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
SkillRise is a new reinforcement learning framework that helps large language model agents solve related yet distinct tasks more efficiently. It organizes tasks into sequences and uses a single policy to alternate…
DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data
The paper proposes a framework called DataOrchestra that learns to curate pre-training data example-by-example rather than applying a uniform strategy across many examples. The framework decides whether to drop, clean…
ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams
A new benchmark called ERUnderstand has been introduced for evaluating the ability of Vision-Language Models (VLMs) to understand Entity-Relationship Diagrams (ERDs), which are important in database design. The…
Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifiers
Researchers present a new framework called RecursiveECG that uses a language model (LLM) to improve ECG classifiers by analyzing the reasons for individual case failures and suggesting targeted revisions based on…
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
The paper focuses on improving the multi-turn long-horizon planning for foundation model agents. The authors introduce a controlled environment to study the acquisition, shaping, and integration of planning abilities…
Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
Researchers propose a new framework called Agent-Guided Concept Discovery to improve the clinical adoption of deep learning models for surgical margin assessment using Rapid Evaporative Ionization Mass Spectrometry…
Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
Researchers propose Agent-Guided Concept Discovery, a framework that helps deep learning models interpret REIMS data for surgical margin assessment by learning meaningful concepts directly from data without predefined…
Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
Researchers propose a new framework called Agent-Guided Concept Discovery for improving deep learning models used in surgical margin assessment. The model learns meaningful concepts directly from data without requiring…
Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks
Researchers introduced an open-source framework to evaluate the effectiveness of AI agents powered by open-weight large language models (LLMs) in data preparation tasks for longitudinal population studies. The study…
AI Assistants Overassist
Researchers introduce Int-Bench, a tool to evaluate how AI language models intervene during problem-solving tasks across code debugging, mathematics, and brain teasers. The study finds that AI models provide more…
AREX: Towards a Recursively Self-Improving Agent for Deep Research
The paper introduces a new type of research agent called AREX, which can recursively improve its answers by verifying intermediate results and using the partially verified state to guide subsequent refinement. The…
AREX: Towards a Recursively Self-Improving Agent for Deep Research
The paper introduces a new family of agents called AREX for deep research. These agents are designed to recursively improve their answers by verifying intermediate results, guiding subsequent refinement, and learning…
Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections
A new approach called Master-Agent Proto-plan System (MAPS) is proposed to improve the coordination of autonomous vehicles at unsignalized intersections. MAPS uses a hierarchical deep reinforcement learning…
Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections
Researchers present MAPS, a deep reinforcement learning architecture for coordinating autonomous vehicles at unsignalized intersections. The system uses a central Master agent that generates a global coordination…
GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG
The authors introduce GRADRAG, a framework for improving Retrieval-Augmented Generation (RAG) systems by coordinating improvements across multiple agents in the pipeline, rather than optimizing components in isolation…
GraphVid: Interactive Graph-Controllable Video Generation
The researchers introduce GraphVid, a model that generates interactive videos using structured interaction graphs, allowing for flexible and precise control. The model shows strong performance compared to Motion-I2V in…
ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders
The paper introduces ICAE-Bench, a benchmark for evaluating coding agents in interactive project building settings. Instead of being limited to completing code under fully specified instructions, these agents are…
OpenForgeRL: Train Harness-native Agents in Any Environment
OpenForgeRL is an open-source framework for training AI agents using various inference harnesses like Claude Code, Codex, OpenClaw, etc., in diverse environments. The framework allows end-to-end training with standard…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study using OpenAI's gpt-5.6-sol model found that the model gave different advice when presented with a dangerous objective directly compared to when other agents transformed and relayed the direction. When shown an…
Synthetic data generation framework for quality control automation in gravure printing
Researchers have developed a synthetic data generation framework to help automate the quality control process in gravure printing. The framework generates high-fidelity images of common printing defects and uses them…
Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
The paper proposes a solution to ensure reliability in AI agents created by non-engineering users within organizations, through democratized low-code, no-code, and conversational development environments. The proposed…
Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design
Researchers introduce a new model called AAMFM (Antigen-specific Antibody Multimodal Foundation Model) for designing functional antibodies. The model learns unified representations of antibody sequences and structures…
Autonomous Collaborative Learning Among an Ensemble of Tsetlin Machines with Consensus-Based Inference
The researchers propose a decentralized collaborative learning paradigm for an ensemble of Tsetlin Machines (TMs) using consensus-based inference. Each agent has its own private TM model, and they combine individual…
Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting
The paper introduces Cumsum-Composable Phase Transport, a new streaming-native temporal layer for keyword spotting in speech tasks. This method uses unitary rotations to project and transport acoustic frames…
Multi-modal transformer for signal classification in nanopore blockade experiments
Researchers present a deep learning architecture for analyzing complex signals from nanopore blockade experiments. The model, which combines multiple signal representations, outperforms existing methods on a peptide…
Multi-stage Dynamic Selection for Cross-Project Defect Prediction
The paper proposes a new framework for Cross-Project Defect Prediction (CPDP) that addresses distribution shift issues between training and target projects by using a two-stage multiple classifier system selection…
OLEDLM: A Unified Language Model for OLED Molecular Design
Researchers propose a new language model for designing Organic Light-Emitting Diode (OLED) materials. The model generates SMILES sequences of OLED molecules based on specific optoelectronic properties, using a…
PhaseAware: Interpretable Human-in-the-Loop Rehabilitation Scoring with Boundary Monitoring
The study introduces PhaseAware, a framework designed for continuous evaluation of rehabilitation quality during physical therapy sessions. It combines temporal data with phase-specific and body part descriptors to…
Plausibility-Driven Prioritization of Candidate Biomedical Annotations
The paper presents a framework using biomedical knowledge graphs (bioKGs) to estimate the plausibility of candidate biomedical annotations, aiming to guide experts in prioritizing them for manual curation. The approach…
Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection
Researchers have developed an energy-efficient method for Android malware detection using deep learning models, aiming to balance performance and battery life. They used quantized neural networks (QNNs) with reduced…
Test Case Prioritization for DNNs via Neural Collapse Instability
A new method, Neural-Collapse-Inspired Prioritization (NCIP), is proposed to improve test case prioritization for deep neural networks (DNNs) in safety-critical domains where testing budgets are limited. The method…
Variance-reduced Domain Adaptation using Paired Sampling
The paper proposes Paired Sampling for Domain Adaptation (PSDA), a new stochastic variance reduction technique designed for distribution-matching frameworks in unsupervised domain adaptation (UDA) that suffer from high…
Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA
The paper presents a diagnostic framework called FiT (Find before Fine-Tune) to evaluate the suitability of small language models for cybersecurity question-answering tasks. The study finds that fine-tuning these…
PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID
Researchers propose a method called PLAID-PRF to improve the effectiveness of multi-vector dense retrieval models like ColBERT. This method uses centroid-based quantization in PLAID, a model that reduces index size and…
RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency
The paper introduces RAGAL, a locally-hosted AI assistant developed for a Romanian agency's technical support team. The system was designed to function within strict data locality constraints, with no external API…
Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
The authors propose a method to improve the accuracy of automatic speech recognition (ASR) models by controlling the activation of 'verbatim' versus 'intended' transcription styles. They argue that current models…
Automated Discovery Has No Universally Superior Harness
A study investigates the effectiveness of different automated discovery systems (OpenEvolve and TTT-Discover) in various machine learning models and problems. The research finds that no single system consistently…
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
Researchers propose a new method called SOPHIA for controlling the reasoning process of large language models, which are currently uncontrollable despite their extended use. The proposed method involves treating each…
Exploratory and Assimilating Reflection: Reflective Recall Cycle for Long-term Memory
The paper proposes a framework called Exploratory-Assimilating Reflection (EAR) for autonomous agents with limited context window and external memory. EAR aims to improve retrieval performance by combining two…
GigaPath-Flash and GigaTIME-Flash: Efficient Pathology Foundation Models for Whole-Slide and Tumor Microenvironment Analysis
Researchers have developed two efficient deep learning models named GigaPath-Flash and GigaTIME-Flash for whole-slide pathology analysis and spatial proteomics prediction. These models are based on a compact ViT-S tile…
MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models
The paper introduces MADA-RL, a method for fine-tuning compact language models with limited budgets. It specializes the models into generator and critic roles and trains them using a debate-aware learning signal. The…
MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models
Researchers introduce MADA-RL, a framework that improves reasoning performance in compact models (up to 4 billion parameters) while reducing training cost. This is achieved by specializing the models into generator and…
O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
Researchers have developed a new method for Industrial Video Anomaly Detection (IVAD) that aims to identify unusual objects and events in industrial processes. This method is designed to work in complex settings where…
Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective
Researchers propose a simple method to merge large language models with significantly different parameters without training or alignment by using dimensional adaptation and ratio-controlled interpolation. The method…
SGA: Plug&Play Geometric Verification for Educational Video Synthesis
Researchers have proposed a new tool called Symbolic Geometric Agent (SGA) to improve the spatial correctness and visual legibility of educational videos generated by Large Language Models (LLMs). The SGA intercepts…
Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation Detection
Researchers propose SIEVE, a framework for detecting video misinformation by first identifying key pieces of evidence that contribute to the decision, and then verifying the veracity based on these identified pieces…
Stress Testing Concept Erasure with Large Language Model Agents
The paper introduces a new framework called Stress Testing Agents for Concept Erasure (STACE). STACE uses multiple Large Language Model (LLM) agents to stress-test models that have had certain concepts erased from…
Concept-Guided Spatial Regularization for World Models in Atari Pong
Researchers evaluated five world model agents in Atari Pong and found failures in visual and dynamical aspects of the generated trajectories by these agents. They propose a method called Concept-Guided Spatial…
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
The authors show that fine-tuning language models on specific datasets can cause broad shifts in ideology across various topics, even when the training data is factually defensible and moderation-passing. This…
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs
Researchers show that fine-tuning language models on specific policies or domains can cause broad ideological shifts across various topics, even when the data used is factually defensible and moderation-passing. This…
Latent Trajectory Discrimination for AI-Generated Text Detection
The paper presents a new approach for detecting AI-generated text called Geometric Trajectory and Contrastive Learning (GTCL). Instead of treating documents as static objects, GTCL models how textual representations…
Latent Trajectory Discrimination for AI-Generated Text Detection
In this paper, the authors propose a new approach for detecting AI-generated text called Geometric Trajectory and Contrastive Learning (GTCL). Unlike existing methods that focus on aggregate statistics or global…
Long-Context Fine-Tuning with Limited VRAM
Researchers introduce Hierarchical Global Attention (HGA) to reduce memory usage during long training sequences in large language models. They use segment-wise backpropagation, tiered KV storage, and detach older data…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Researchers have created a new benchmark called MM-IssueLoc to evaluate the effectiveness of multimodal repository-level issue localization, which includes visual evidence such as screenshots and logs. Current…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Researchers have introduced a new benchmark called MM-IssueLoc for evaluating the effectiveness of systems in repository-level issue localization that also includes visual evidence such as screenshots, error dialogs…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Researchers introduce MM-IssueLoc, a benchmark and evaluation protocol designed specifically for repository-level issue localization with visual evidence. The dataset includes 652 issue-PR instances across multiple…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
The paper introduces MM-IssueLoc, a benchmark and evaluation protocol for repository-level issue localization that includes visual evidence. The benchmark has 652 issue-PR instances across 23 languages with annotations…
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
The paper introduces MM-IssueLoc, a new benchmark and evaluation protocol for repository-level issue localization with visual evidence. The benchmark contains over 650 issue-PR instances across multiple languages…
Reachability-Aware Pretraining for Efficient Target-Oriented Path Exploration in Temporal Knowledge Graph Reasoning
The authors propose a new method called RAPTOR for improving the efficiency of target-oriented path exploration in temporal knowledge graphs (TKG). The method injects a reachability-aware inductive bias to the agent…
Scaling Behavior Foundation Model for Humanoid Robots
Researchers propose a scaling recipe for Behavior Foundation Models (BFMs) to improve the capabilities of humanoid robots. The recipe includes a learning paradigm, strategic synergy between data collection methods, and…
Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution
Researchers propose a graph neural network approach to detect and analyze reasoning structures in large language models (LLMs) generated texts for improved robustness against paraphrasing and obfuscation techniques…
Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution
The paper proposes a new method for detecting text generated by large language models (LLMs) and attributing authorship to them. The method goes beyond just analyzing surface-level linguistic features and instead…
teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data
Researchers developed teLLMe, a system that allows traffic agencies to analyze urban driving data using causal analysis methods. The system helps answer questions about the impact of various factors on traffic density…
Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic System
The MEDA system is an automated framework using Large Language Models (LLMs) and Symbolic Regression (SR) to discover Ordinary Differential Equations (ODEs) for biological systems. It retrieves background knowledge…
Experience Memory Graph: One-Shot Error Correction for Agents
Researchers propose a new framework called Experience Memory Graph (EMG) to help large language model agents recover from failures more effectively in complex, long-horizon tasks. Instead of using prompt-based…
Experience Memory Graph: One-Shot Error Correction for Agents
The researchers propose a new framework called Experience Memory Graph (EMG) to help large language model agents recover from failures more effectively in complex, long-horizon tasks. EMG reformulates failure recovery…
Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs
Researchers propose a new method called Grounded Context Preference Optimization (Groc-PO) to improve the truthfulness and utility of Multimodal Large Language Models (MLLMs). Current MLLMs often make errors due to…
Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
The paper proposes a new framework called Memory as a Controlled Process (MemCon) for large language model (LLM) agents that use external memory systems. MemCon learns an online policy to adaptively decide when, what…
Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study
The paper introduces a multi-expert system for Optical Character Recognition (OCR) of historical Manchu texts which have various writing styles and limited labeled data. The system uses a router that classifies pages…
A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism
The study investigates the impact of Reinforcement learning with verifiable rewards and Group Relative Policy Optimization (GRPO) on a small language and vision-language model web agent. The research found that GRPO…
A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism
The research investigates the effectiveness of Reinforcement learning with verifiable rewards and Group Relative Policy Optimization (GRPO) on a small language and vision-language model web agent at scales ranging from…
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
Researchers present Pythia, a multi-agent system that automatically generates and optimizes extraction prompts for clinical concepts without manual engineering or fine-tuning. They compare Pythia with a curated lexicon…
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
A new system called Pythia was developed, which automatically generates and optimizes extraction prompts for clinical concepts without the need for manual prompt engineering or fine-tuning. The researchers compared…
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
Researchers train a discrete diffusion language model to transcribe speech instead of using autoregressive decoders that emit one token at a time. The model is based on a mixture-of-experts called DiffusionGemma, and…
Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models
In this research, Mehmet Iscan introduces a method called PoPE (Popperian Placebo-controlled Evaluation) to test the effectiveness of Frozen small code LLMs in self-repair when faced with errors. The study compares…
Tracing Agentic Failure from the Flow of Success
The paper proposes a new method called OAT (One-Class Attribution for Tracing) for identifying errors in language models without relying on expensive or difficult-to-collect data. This method is faster and more…
UR-VC: Unsupervised Robotic Value Correction for Time-Derived Progress Proxies
Researchers introduce an offline method called Unsupervised Robotic Value Correction (UR-VC) to correct time-derived progress labels used by modern robot learning systems. The method is based on a regularity in…
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
The authors present a method for creating and refining evaluation metrics for self-improving language models (LLMs). The proposed method, called Double Ratchet, evolves metrics by combining small drawback detectors in…
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
The paper presents a method for creating and improving self-evolving agent systems, which are capable of developing, modifying, and discarding their own skills. The authors claim that in many real-world applications, a…
Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming
Researchers present AHA, an automated red-teaming approach for production language models like Claude Code and Codex. AHA discovers reusable vulnerability knowledge about other agents by proposing a vulnerability…
Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning
A new method using reinforcement learning (RL) has been proposed to improve the accuracy of decoding continuous three-dimensional motor imagery signals from non-invasive EEG data for brain-computer interfaces (BCIs)…
Metacognition in LLMs: Foundations, Progress, and Opportunities
This research paper provides a comprehensive overview of the current state of metacognition in Large Language Models (LLMs). The authors discuss recent advancements, methods, and benchmarks for measuring and evaluating…
MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents
Researchers introduce MM-ToolSandBox, a new evaluation framework for visual tool-calling agents. This framework supports over 500 tools across 16 application domains and can handle multi-image, multi-turn tasks with…
AI-guided stimuli discovery and generation to optimize facial emotion perception studies in autism
Researchers have developed a method to create and select facial expressions that enhance differences in emotion perception between autistic and neurotypical adults. This is done by training artificial neural networks…
CommuniWave:A Machine Learning Model for Quantifying the Degree of Temporary Informal Behavior in Urban Communities
Researchers have developed a machine learning model named CommuniWave. This model aims to help urban managers and designers by efficiently detecting and quantifying temporary informal behaviors in urban communities…
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
The authors of the paper 'Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph', published in 2026, discuss a new approach to utilizing the internal k-nearest-neighbor (kNN) graph constructed…
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
The paper proposes a method for machine learning that aims to align autonomous agents' behavior with human intent in diverse operational contexts by using a hierarchical machine teaching algorithm for reward learning…
OpenCoF: Learning to Reason Through Video Generation
The paper introduces OpenCoF, a framework that includes a new dataset and a fine-tuned video model for improving Chain-of-Frame (CoF) reasoning in video generation. The authors argue that existing models lack specific…
Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction
A new method called BioModule is proposed for predicting biomechanical attributes from standard 3D skeletons recovered from human motion, without requiring modifications to the upstream pose model. The method is…
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
The paper proposes ProjAgent, a new system for generating code at the repository level by introducing 'procedural similarity' as a retrieval signal. This method decomposes the target function into steps and retrieves…
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
The paper introduces ProjAgent, a system for generating code at the repository level that considers procedural similarity as a new method for retrieving appropriate functions. ProjAgent deconstructs target functions…
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
The paper proposes ProjAgent, a system for generating code at the repository level. It introduces 'procedural similarity' as a new way to retrieve relevant functions, addressing a limitation of existing methods that…
Self-Adaptive Anomaly Detection with Reinforcement Learning and Human Feedback in Connected Vehicles
The paper presents an online anomaly detection framework for connected vehicles that uses a deep Q-network with self-attention to select suitable detectors, an ensemble of statistical drift detectors to monitor input…
Self-Adaptive Anomaly Detection with Reinforcement Learning and Human Feedback in Connected Vehicles
The paper proposes an online anomaly detection framework for autonomous cyber-physical systems (CPS), specifically connected vehicles, that combines three coordinated mechanisms: a deep Q-network with self-attention to…
SLORR: Simple and Efficient In-Training Low-Rank Regularization
The paper introduces SLORR, a simple and efficient method for in-training low-rank regularization of neural networks. It addresses the limitations of existing methods by being stateless and preserving the original…
SLORR: Simple and Efficient In-Training Low-Rank Regularization
The paper introduces SLORR, a simple and efficient low-rank regularization method for compressing neural networks during training. It addresses the limitations of existing methods by being stateless…
SLORR: Simple and Efficient In-Training Low-Rank Regularization
The paper introduces SLORR, a simple and efficient in-training low-rank regularization framework for neural networks. It aims to improve compressibility without significant accuracy loss, while avoiding the limitations…
SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling
The paper proposes SMetric, a new scheduling method for Large Language Models (LLMs) in serving agents. The method aims to balance the session-centric workload of agents and increase Key-Value (KV$) reuse by…
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
This research study introduces a new metric, called 'correctness agreement', to evaluate the impact of post-training quantization on large language models. The authors show that even when task performance seems…
TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories
The paper introduces TRACE, a new agent watermark system designed to withstand manipulation by resellers who may alter or replace an original agent. The system works by embedding two channels into the agent's behavior…
UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing
UltraX is a new framework designed to improve the quality of large-scale pre-training data for Large Language Models (LLMs). It addresses the limitations of existing methods by offering fine-grained instance-level…
WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving
Researchers propose WCog-VLA, a dual-level model for autonomous driving, which combines semantic world forecasting and generative world evolution to bridge the gap between reactive and proactive driving. The semantic…
WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search
Researchers propose a new framework called WebSwarm for deep and wide web searches using large language models (LLMs). The framework aims to improve the ability of single agents to handle complexity and coverage…
MIRA-Math: A Benchmark for Minimal Information Requesting and Mathematical Reasoning
The researchers introduce MIRA-Math, a benchmark for testing AI models' ability to ask for and integrate missing facts to solve mathematical problems. The benchmark contains 2310 instances from 22 mathematical families.
Physics-Audited Agentic Discovery in Scientific Machine Learning
The paper introduces Physics-Audited Agentic Scientific Machine Learning (PA-SciML), a new workflow that verifies the accuracy of surrogate models discovered by large language model agents in scientific machine…
Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents
Researchers study a failure mode in tool-using Language Model (LLM) agents, where they violate policies without appearing to do so, leading to silent errors such as cancelled bookings or unverified claims. A…
Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26
The authors present Reward-Adaptive Iterative Discovery (RAID), a new approach for automated game testing using Reinforcement Learning (RL) in the gaming industry. The case study is based on EA SPORTS NHL 26's…
RLVP: Penalize the Path, Reward the Outcome
The paper 'RLVP: Penalize the Path, Reward the Outcome' by Bojie Li and Noah Shi proposes a method for training artificial agents to perform tasks effectively in real-world environments. This method addresses two main…
SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents
The paper introduces SkillCenter, a large-scale skill library for autonomous AI agents, containing 216,938 structured skills across 24 domain bundles. The skills are obtained from various sources like peer-reviewed…
Stability of Flow Models for Graph Signals
The paper presents research on the stability of continuous flow models for generating signals on graphs. The authors analyze normalized flow models parameterized by Graph Neural Networks (GNNs) and demonstrate that…
SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation
Researchers have developed a method called SynthAVE to generate large amounts of labeled data for e-commerce attribute extraction using synthetic labels validated by multiple large language models (LLMs). The benchmark…
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
The researchers explore the impact of biased judges in self-evolving agents, focusing on skill retirement, a mechanism that helps maintain the quality of an agent's knowledge base by retiring poorly performing skills…
When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
The paper proposes ARGTCA, a method to improve the calibration of Vision-Language Models (VLMs) by using Graph Attention Networks to capture inter-attribute dependencies and reduce overconfidence during test-time…
A Physics-Informed Neural Network Framework for Elastodynamic Wave Propagation in Bimaterial Systems
A new study presents a Physics-Informed Neural Network (PINN) framework to model the transient elastodynamic wave propagation in bimaterial systems, specifically focusing on a steel-aluminum specimen. The PINN…
An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery
The researchers propose an experimental design framework to systematically evaluate the autonomous model discovery behavior of large language model coding agents, like Codex and Claude Code. The framework considers…
DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression
The research introduces DepthWeave-KV, a new cache compression method for long-context language models. This method adapts to the needs of different tokens by factorizing key and value states across neighboring…
Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs
The researchers evaluate the performance of uncertainty estimation methods across 22 languages in high-, mid-, and low-resource settings using two human-curated question and answer datasets. They compare open and…
FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference
The paper introduces FreqDepthKV, an inference-time cache compression method for long-context LLM (Large Language Model) inference that reduces memory and bandwidth costs while maintaining task accuracy on various…
Multi-Agent Deep Reinforcement Learning for Multi Objective Battery Management in Dairy Farms
This research introduces a multi-objective optimization control system for battery management in dairy farms that utilizes differential evolution and multi-agent deep reinforcement learning. The system aims to improve…
Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval
The authors propose a method called SkillReranker to improve the ability of agent systems to complete complex tasks by accurately selecting skills from large libraries. The method involves semantic decomposition of…
TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting
The paper introduces TopoBrick, a new framework for forecasting IoT data in buildings without requiring training. It uses building knowledge graphs to create a structural skeleton and employs an agentic topology…
VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection
The paper introduces VendorBench-100, a benchmark for evaluating deepfake image detection models across three paradigms: commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors. The…
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
Researchers developed a machine learning model that can classify transient candidates in time-domain surveys, known as Real-Bogus classification, without needing human-labeled data. The model is trained using simulated…
LLM-as-a-Verifier: A General-Purpose Verification Framework
In this research, a general-purpose verification framework called LLM-as-a-Verifier is introduced. This framework provides detailed feedback for agentic tasks without requiring additional training. The framework…
Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing
In this research, the authors propose Localized LoRA-MoE, a framework that combines localized spatial blocking with dynamic, context-conditioned routing for Large Language Models (LLMs) and high-dimensional perception…
Multiplayer Interactive World Models with Representation Autoencoders
Researchers present a new model for multiplayer interactive worlds, specifically designed for complex environments like Rocket League with fast-paced, coupled dynamics. The model is trained on 10,000 hours of gameplay…
PDEFlow: Autonomous Agentic PDE Pipelines for Neural Operator Learning and Solver-Free Inference
The paper presents PDEFlow, a framework that converts user-level descriptions of ODEs and PDEs into neural operator pipelines for autonomous agentic simulations. It includes stages for problem specification, data…
TacReasoner: A Dynamic Tactile-Language Framework for Interactive Reasoning in Real-World Scenarios
The paper proposes TacReasoner, a new framework that enhances the perception and representation of dynamic tactile signals for intelligent systems. It addresses two challenges: insufficient modeling of such signals and…
TREK: Distill to Explore, Reinforce to Refine
The research presents TREK (Teacher-Routed Exploration via Forward KL), a method that uses distillation for exploration support expansion, rather than imitation. This method can be used with various types of teachers…
TREK: Distill to Explore, Reinforce to Refine
The paper proposes a method called TREK (Teacher-Routed Exploration via Forward KL) to improve Group Relative Policy Optimization (GRPO). TREK uses distillation for exploration support expansion and can work with…
Unified Audio Intelligence Without Regressing on Text Intelligence
The researchers introduce a unified audio-text language model called Audex, which is built on a strong text-only model. Audex allows for strong fusion of audio and text, seamless multimodal generation, and…
Automated grading of Linux/bash examinations using large language models: a four-level cognitive taxonomy approach
The paper evaluates whether four large language models can approximate the judgement of experts when grading Linux/bash command responses from second-year Computer Engineering students. The study uses a four-level…
Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom Networks
The paper proposes a Guard Rail Validation (GRV) framework to ensure autonomous decisions made by AI agents in fully autonomous telecom networks are valid before they cause live network changes. The framework evaluates…
Distributed Attacks in Persistent-State AI Control
Researchers introduce Iterative VibeCoding, a setting for AI control that studies the deployment of autonomous AI coding agents and their potential for distributed attacks. The study finds that gradual attacks, which…
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
A new evaluation setting called Autonomous Policy Evolution (APE) is introduced in a benchmark named EvoPolicyGym, which is used to test how autonomous agents iteratively improve their policy systems within a fixed…
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
In the research paper titled 'EvoPolicyGym', the authors introduce a controlled evaluation setting called Autonomous Policy Evolution (APE) for assessing how autonomous agents iteratively improve their executable…
Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics
The paper presents an autonomous research pipeline that can conduct end-to-end research from a corpus of 11,083 recent condensed matter physics papers to a publication-grade manuscript. The agent is capable of…
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
Researchers propose Task-Agnostic Pretraining (TAP), a two-stage framework to train Vision-Language-Action (VLA) models. TAP first learns transferable motor priors from unlabeled interaction data using self-supervised…
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
The authors propose a new programming paradigm called fuzzy-function programming, where functions can be compiled from natural language specifications into compact, locally executable neural networks. They introduce…
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
Researchers present two contributions aimed at improving speaker recognition in long-form TV dramas. They create a large-scale benchmark called DramaSR-532K with over 900 characters and propose using a large reasoning…
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
The paper introduces a new benchmark, DramaSR-532K, for speaker recognition in long-form TV dramas. They also propose a new approach called DramaSR-LRM which uses a large reasoning model (LRM) to aggregate contextual…
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Researchers propose a new method called Recursive Evidence Replay (RECONTEXT) to improve long-context reasoning in large language models without requiring additional training, memory, or context pruning. RECONTEXT…
Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
Researchers introduce OpenAgent, a problem setting to test how well AI agents can generalize their skills from static benchmarks to real-world scenarios with dynamic user queries and tools. The study finds that both…
DART-VLN: Test-Time Memory Decay and Anti-Loop Regularization for Discrete Vision-Language Navigation
The researchers present DART-VLN, a test-time control framework for vision-language navigation agents that aims to improve their performance by addressing two common issues: stale historical evidence at memory readout…
Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows
A study identifies common failures in generating and executing analytical workflows using large language models across finance, human resources, and public safety domains. The authors found five recurring classes of…
GPU-Parallel Linearization Error Bounds for Real-Time Robust Optimal Control of Nonlinear and Neural Network Dynamics
The paper presents a new method called GPUSLS-LEO for real-time robust optimal control of uncertain nonlinear systems, specifically focusing on systems with linear time-varying (LTV) approximations. This method…
LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution
The authors present LLVM-Bench, a large-scale benchmark for testing the effectiveness of large language models (LLMs) in resolving issues related to the LLVM compiler. They found that current LLM-based techniques are…
Measuring the Gap Between Human and LLM Research Ideas
The authors explore the gap between ideas generated by Large Language Models (LLMs) and those of human researchers in the field of computer science. They develop an evaluation framework based on high-quality human…
FARS: A Fully Automated Research System Deployed at Scale
The paper introduces FARS, a fully automated AI research system that can generate, execute, and write complete research papers on various AI/ML topics. In its first public deployment, FARS produced 166 papers while…
FLORA: A deep learning approach to predict forest attributes from heterogeneous LiDAR data
Researchers present FLORA, a deep learning framework that uses LiDAR data and auxiliary variables to predict six forest attributes in mainland France. The model outperforms season-specific models and achieves an rRMSE…
GR2 Technical Report
Researchers present GR2 (Generative Reasoning Re-Ranker), a framework designed to improve the performance of recommendation systems in an industrial setting. The system combines mid-training on semantic IDs…
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
Researchers have developed two new mechanisms - Reinforcement Learning with Metacognitive Feedback (RLMF) and Metacognitive Data Selection - to improve the performance of Language Models (LLMs). The goal is to make…
TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models
Researchers have proposed a multi-agent system that uses expert decision trees and Vision-Language Models (VLMs) to automate the bias classification in tree height in forestry remote sensing. The system mitigates VLM…
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
The paper proposes a new framework called TRIAGE for credit assignment in agentic reinforcement learning. This framework adds a semantic role axis to outcome credit, aiming to correct the issues of standard GRPO where…
A Multi-task Mixture of Experts Framework for Malware Classification, Packing Detection, and Family Attribution
Researchers propose a new multi-task malware analysis framework based on Mixture of Experts (MoE) architectures. The system can classify malware families, detect packed versus unpacked malware, and identify malware…
Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
The paper 'Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents' discusses the concept of always-on agents, which are systems that have a durable state accumulated from past interactions…
BayesEvolve: Explicit Belief States for Autonomous Scientific Discovery
The paper introduces a new framework called BayesEvolve for autonomous scientific discovery. This framework aims to improve the efficiency of experimentation by maintaining explicit, uncertainty-aware beliefs about…
DOPD: Dual On-policy Distillation
The paper proposes a new method called Dual On-policy Distillation (DOPD) for transferring knowledge from a teacher model to a student model in on-policy distillation. DOPD aims to address the issue of 'privilege…
ManimAgent: Self-Evolving Multimodal Agents for Visual Education
Researchers present ManimAgent, a self-evolving multimodal agent that uses a dual-channel Episodic Memory Bank to carry reflection experience across tasks in generating Python code using the Manim library for…
Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
This research presents a theoretical framework that explains why certain 'discarded' norms in contrastive embedding models, which were thought to be ignored during training, actually correlate with semantic properties…
PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning
Researchers propose a new framework called PromptGNN-sim to improve the performance of Text-Attributed Graph Learning tasks. The method combines Graph Attention Network (GAT) and Language Model (LLM) in a…
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
Researchers collect and release a dataset of approximately 4,300 coding-agent sessions from their own use of Claude Code and Codex. The data shows that coding-agent workloads feature long autonomous loops, long…
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
Researchers have collected and released a dataset of 4300 coding agent sessions, containing around 350,000 LLM steps and 430,000 tool calls from their own use of Claude Code and Codex. The analysis shows that…
UNKNOWN
The text does not provide a summary or brief.
UNKNOWN
The text does not provide a summary.
Confidence-Aware Tool Orchestration for Robust Video Understanding
The researchers propose a framework called Robust-TO for video understanding that addresses the 'Blind Trust Problem' in video reasoning language models. The proposed method incorporates per-frame trustworthiness into…
Einstein World Models
The paper proposes Einstein World Models (EWMs), a system for large language models (LLMs) to reason about counterfactual events using visual-temporal rollouts, enhancing their capability beyond language alone. The…
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
The research introduces a method called Planning Experience Exploration and Utilization (PEEU) to improve the task planning capabilities of smaller open-source Multi-Language Model Learning Machines (MLLMs). These…
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
Researchers introduce a new method called PEEU to improve the task planning capabilities of small, open-source multimodal web agents that assist humans in operating repetitive graphical user interface (GUI) tasks…
Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation
The study shows that Language Models (LLMs) fine-tuned for security classification can have vulnerabilities missed during standard evaluation because they learn token-level indicator semantics that work well on their…
Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation
The study shows that Language Models (LLMs) fine-tuned for security classification may overlook vulnerabilities introduced during fine-tuning itself. These models can learn token-level indicator semantics that preserve…
Joint Learning of Experiential Rules and Policies for Large Language Model Agents
The paper introduces a new method called Joint Learning of Experiential Rules and Policies (JERP) for large language model agents operating in multi-step interactive environments. The main challenge addressed is…
OpenRCA 2.0: From Outcome Labels to Causal Process Supervision
The paper introduces OpenRCA 2.0, a new benchmark for root cause analysis (RCA) of Large Language Models (LLMs). The new dataset, OpenRCA 2.0, includes 500 instances and is the first cross-system RCA benchmark with…
OpenRCA 2.0: From Outcome Labels to Causal Process Supervision
The paper introduces OpenRCA 2.0, a new benchmark for root cause analysis (RCA) of large language models (LLMs). The benchmark includes step-wise causal annotations for LLMs and addresses the issue that existing…
ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models
The paper proposes a new method called Reasoning-guided progressive Open Relation Extraction (ReaORE) to improve the performance of Open Relation Extraction (OpenRE). This method addresses the limitations of current…
Semantic Early-Stopping for Iterative LLM Agent Loops
The research presents a method called semantic early-stopping for multi-agent large language model (LLM) loops, such as a Writer and a Critic. The goal is to halt the loop when the consecutive draft embeddings no…
Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text
The paper presents GAversary, a new method for generating adversarial attacks on natural language models using a Genetic Algorithm (GA). This method is able to reduce the accuracy of several target models significantly…
Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text
Researchers have developed a new method called GAversary, which uses a Genetic Algorithm (GA) and GloVe embeddings to generate adversarial attacks on natural language models. These attacks can significantly reduce the…
When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models
The study examines the use of multiple language models (LLMs) to improve accuracy over single models and finds that their performance is limited by a factor called 'beta'. Beta represents the rate at which all models…
A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG welding
Researchers have developed a new approach to improve the performance of deep learning models in predicting weld penetration status, especially when transferring between welding processes with distinct physical…
Autodata: An agentic data scientist to create high quality synthetic data
Researchers introduce Autodata, an AI agent that can act as a data scientist to create high-quality synthetic data for various tasks like computer science research, legal reasoning, and mathematical object reasoning…
FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
The research introduces FORCE, a three-stage framework for fine-tuning Vision-Language-Action (VLA) models using Reinforcement Learning (RL). The framework addresses sample inefficiency issues by implementing a…
GUI agent: Guided Exploration of User-Sensitive Screens
This research presents a new agent called Guided Exploration of User-Sensitive Screens (GUI agent) designed to automate tasks within an open Graphical User Interface (GUI) environment. The GUI agent is intended to…
Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization
The authors present HiReLC, a framework that uses reinforcement learning to automatically compress deep neural networks by pruning and quantizing them. The framework works in two levels: low-level agents (LLAs)…
Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound
The paper introduces Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound (MAGR-BB), a method for inferring which agents are working together and what each…
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Researchers present a new method called 'progress advantage' for evaluating Language Learning Models (LLMs) without the need for dedicated reward model training. This method is based on reinforcement learning (RL)…
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
The paper discusses a method called On-policy Self-Distillation, which uses a single model as both teacher and student to achieve high accuracy in pass@1. However, it is found that this method can lead to a decrease in…
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment
Researchers have proposed a framework called SARA (Semantically Anchored Routing Alignment) to improve the performance of multilingual language models in low-resource languages. The framework aligns the routing…
The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
The authors propose a safety mechanism for AI agents called the Unfireable Safety Kernel, which is designed to prevent AI systems from making unauthorized changes within their own runtime. The kernel is implemented in…
Beyond U-Net: A Latent-Representation-Aligned Skip-Free Backbone for Flow-Matching Speech Enhancement
The authors propose a new method for speech enhancement using flow-matching, which is more efficient than generative models with iterative sampling processes that limit real-time deployment. Their approach involves a…
Can Scale Save Us From Plasticity Loss in Large Language Models?
Researchers studied plasticity loss, a challenge in creating neural networks capable of continuous learning, in modern transformer-based language models (LLMs). They found evidence of plasticity loss across various…
EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence
Researchers have developed a new benchmark called Evidence-Grounded Video Question Answering Benchmark (EG-VQA) to evaluate the performance of video question answering models. The benchmark is unique because it…
FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction
Researchers propose a new method called FlowPipe to automatically construct data preparation pipelines for machine learning. The proposed method uses Conditional Generative Flow Networks (C-GFlowNets) and Deep Semantic…
Large-Language-Model Discovery of Quantum LDPC Codes through Structured Concept Evolution
Researchers have developed a new method called Structured Concept Evolution (SCE) that uses a large language model and structured algebraic mutation grammar to discover Quantum Low-Density Parity-Check (qLDPC) codes…
OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis
The researchers introduce OrbitForge, a method that converts single text-generated videos into 3D scenes using frozen video priors and per-prompt Gaussian Splatting reconstruction optimization. The method uses 3D…
Poster: Exploring the Limits of Audio-Based Detection of Turkish Phone Call Scams
Researchers introduce a new dataset of Turkish phone call conversations to test large language models' ability to detect scams. They find that using corrected or uncorrected transcripts improves results compared to…
Quant Convergence: Bridging Classical Value Investing and Modern Factor Models for Systematic Equity Selection
This research explores the effectiveness of Benjamin Graham's classic value investing rules in comparison to complex machine learning models in the context of equity selection. The study found that the pure Graham…
Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation
Researchers propose a framework for training Computer-Use Agents (CUAs) using reinforcement learning and autonomous vision-language evaluation. This method provides a scalable supervision signal, improving success…
RetiSEM: Generalising Causal Models for Fragmented Biomedical Data
A new method called RetiSEM is proposed to learn causal models from fragmented biomedical data, where clinical, molecular, and imaging variables are often incomplete or not jointly observed. The method organizes…
Scaling Laws for Task-Specific LLM Distillation
This research provides empirical scaling laws for compressing Large Language Models (LLMs) specifically for certain domains, focusing on quantitative finance as the application domain. The study investigates the impact…
When CQs Go Wrong: Challenges in CQ Verification with OE-Assist
This research paper discusses the challenges faced during Competency Questions (CQ) verification, a crucial step in ensuring that an ontology accurately represents its intended purpose. The authors found that CQs can…
Data Selection Through Iterative Self-Filtering for Vision-Language Settings
Researchers propose a new method to select data for training neural networks in large scale, noisy datasets. The Self-Filtering method iteratively trains a CLIP model on an evolving dataset, balancing clean samples and…
Detecting Malicious Agent Skills in the Wild using Attention
The research presents a two-stage detector called Locate-and-Judge for identifying malicious skills in Language Model (LLM) agents. These skills are third-party packages of instructions that can potentially exfiltrate…
Distribution-Aware Diffusion-LLM for Robust Ultra-Long-Term Time Series Forecasting
The authors propose a new method called Diffusion-LLM for time series forecasting using Large Language Models (LLMs). The proposed framework integrates a conditional diffusion model into an LLM-based forecasting…
Dynamic multi-agent deep reinforcement learning-based pricing and incentivization approach in multimodal transportation networks
A study proposes a multi-agent deep reinforcement learning framework to coordinate shared mobility services (SMSs) and public transport in multimodal transportation systems. The framework aims to improve efficiency…
GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation
The paper presents a method called GRINQH (GRaded INput-based Quantization Hierarchy) to accelerate the decoding process of language models during inference, particularly beneficial for edge-computing settings. The…
Learning Process Rewards via Success Visitation Matching for Efficient RL
Researchers propose a method to make reinforcement learning (RL) more effective when dealing with sparse rewards, which are typically given only when a task is completed. The method incentivizes the RL-learned policy…
RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models
The paper proposes a new approach for training Vision-Language-Action (VLA) models through active, continual learning. This method aims to address the inefficiencies of traditional passive imitation learning by…
RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation
The paper introduces RS-Gen, a multi-stage image agent framework that aims to improve the performance of existing image generation and editing models by introducing a 'Questioning-and-Solving' closed-loop mechanism for…
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct
The paper presents VeriEvol, a framework for scaling reinforcement learning in visual mathematical reasoning. It addresses the challenge of maintaining reliable reward labels as data volume grows by treating scaling as…
VideoAgent: All-in-One Framework for Video Understanding and Editing
Researchers have developed a new framework called VideoAgent to automate video editing tasks. The system can handle diverse editing operations and understand long videos, addressing limitations in existing automated…
