All notes, newest first
2,343 notes. Notes 1,851 to 1,900, page 38 of 47.
Optimal Resource Utilization for Autonomous Laboratory Orchestrators
The authors propose a two-step method to optimize resource utilization in autonomous laboratories, specifically for metal-organic framework synthesis. The first step involves using constraint programming to find the…
Post-Training Pruning for Diffusion Transformers
The paper proposes DiT-Pruning, a method to improve post-training pruning performance for Diffusion Transformers (DiTs), which are used in image generation but have high computational overhead. The new method uses…
Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations
Researchers propose an adversarial generator-discriminator framework to train language models (LM) for tasks with well-defined success metrics, like code generation and mathematical reasoning. The new approach improves…
Self-Evolving Agents with Anytime-Valid Certificates
The text discusses a new architecture called SEA (Self-Evolving Agents) that aims to control self-modification in artificial intelligence systems. The system is designed to have a small steering adapter and a versioned…
Self-Evolving Agents with Anytime-Valid Certificates
In this paper, Biswa Sengupta introduces SEA (Self-Evolving Agents), a new architecture that allows for self-modification in AI agents while maintaining certain guarantees and controls. The architecture consists of a…
Self-GC: Self-Governing Context for Long-Horizon LLM Agents
A research paper titled 'Self-GC: Self-Governing Context for Long-Horizon LLM Agents' presents a system called Self-GC that aims to manage the lifecycle of context objects for long-horizon language models (LLMs). The…
SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned Environments
The paper proposes SenseWalk, an interactive system that uses large language models (LLMs) to simulate semantic trajectories for human movement analysis. The simulation workflow combines LLMs and the social force model…
Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains
Researchers introduce Agent Skill Supply Chains (ASSCs) to manage the dependencies of Large Language Model (LLM) agents by characterizing their dependency graphs. The study finds that ASSCs have four structural…
Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains
Researchers introduce a new method called Agent Skill Supply Chains (ASSCs) to manage dependencies in Large Language Model agents. They develop SkillDepAnalyzer, which extracts dependency graphs and metadata from…
SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests
Researchers propose a new software agent called SWE-Doctor that uses multiple bug reproduction tests (BRTs) to generate more effective patches for resolving software issues. The agent first generates multi-faceted…
SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests
A study was conducted to improve software engineering agents that generate patches for software issues. The researchers found that using bug reproduction tests (BRTs) directly to guide patch generation can be…
The State-Prediction Separation Hypothesis
Researchers propose a new model for language modeling called 'state-prediction separation' which aims to improve efficiency by separating the prediction of the next token and the storage of useful state for future…
Theoria: Rewrite-Acceptability Verification over Informal Reasoning States
Theoria is a verification architecture proposed by Ben Slivinski and Michael Saldivar that aims to close the gap between formal proof assistants and scalar LLM judges in determining when an AI system's answer can be…
Theoria: Rewrite-Acceptability Verification over Informal Reasoning States
Theoria is a verification architecture presented by Ben Slivinski and Michael Saldivar that aims to address the issue of trust in AI systems' answers. It rewrites candidate solutions into a sequence of typed state…
Two AI Metrics Diverged: Will it Make All the Difference?
The authors discuss how different metrics for evaluating AI capabilities can lead to varying conclusions about whether advanced AI will remain in the hands of a few powerful entities or become more accessible to…
A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems
This research paper discusses the increased role of large language models in various systems beyond just text generation, and how this shift changes the security landscape. The authors systematize the existing…
A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols
The paper presents ProtoPilot, a self-evolving multi-agent system designed to automate the generation and execution of biological protocols. The system achieved high success rates in various tasks compared to…
A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols
Researchers have developed a self-evolving multi-agent system called ProtoPilot for automated generation and execution of biological protocols. The system incorporates various components to ensure alignment between…
A Technical Typology of AI Systems in Public Administration
The paper argues that different types of AI systems impact public values like accountability, procedural justice, and non-discrimination differently. The authors propose a typology of five AI system categories…
A Technical Typology of AI Systems in Public Administration
The paper argues that research on AI in public administration should be more precise about different types of AI systems. The authors present a typology of five categories of AI systems, evaluate the precision of…
A Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agents
This research paper proposes a framework for using Large Language Model (LLM) agents to support operators in recovering from faults in process plants. The LLM is used as a constrained supervisory planner, proposing…
ACE: Pluggable Adaptive Context Elasticizer across Agents
Researchers propose a new module called Adaptive Context Elasticizer (ACE) to address the challenges posed by growing trajectory lengths in large language models (LLMs) with fixed context windows. ACE is designed to be…
AdaJEPA: An Adaptive Latent World Model
The paper proposes a new adaptive latent world model called AdaJEPA that can improve planning accuracy by continuously recalibrating the world model during test-time, particularly when dealing with distribution shift…
Adaptive Cluster-First Route-Second Decomposition for Industrial-Scale Vehicle Routing
The researchers propose an adaptive system for solving large-scale capacitated vehicle routing problems (CVRPs). The system uses a large language model (LLM) as a high-level decision maker to analyze the evolving…
An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping
The text discusses an AI framework designed to expedite the discovery process in plant phenotyping at Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory (APPL). The framework aims to automate the…
An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping
A new AI framework developed at Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory aims to automate the analysis of large plant imaging datasets generated by automated stations. The framework…
Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference
The paper proposes a method for improving the efficiency of multimodal large language models (MLLMs) by selectively skipping redundant attention and FFN operators during visual-token processing. The method aims to…
AxDafny: Agentic Verified Code Generation in Dafny
The paper presents AxDafny, a framework for generating executable code and verification artifacts in Dafny using a verifier-guided repair approach. The framework significantly improves verification success over the…
AxDafny: Agentic Verified Code Generation in Dafny
Researchers present AxDafny, a framework for generating executable code and proof artifacts in Dafny using a verifier-guided repair method. The study uses a benchmark called LiveCodeBench-Pro-Dafny with 250 programming…
Better Understanding, Understanding Better
The paper introduces a comparative epistemic logic of understanding with level-indexed understanding modalities and a comparative connective for comparing the understanding of different agents. The framework is…
Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
The paper introduces Medical Reasoning-aware Policy Optimization (MRPO), a reinforcement learning algorithm for medical multimodal reasoning, which aims to optimize the reasoning process and reduce cascading errors…
Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling
Researchers propose a method called CRAFT to improve traffic simulation in closed-loop environments. The proposed method aims to mitigate a local-to-global context mismatch that occurs when autoregressive traffic…
Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling
The research proposes a method called CRAFT to address a problem where traffic simulators trained on local data perform poorly in global environments due to a lack of complete context. The proposed method involves…
Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian
Researchers investigated cross-lingual relation extraction for Romanian using large language models (LLMs) and an English to Romanian translation pipeline. They evaluated a 31B LLM under different configurations…
Design and Implementation of Agentic Orchestrations and Orchestration of Agents
The paper discusses a framework for managing AI agents in a way that balances their autonomy with traceability and tractability. It presents various methods for orchestrating these agents, along with qualitative…
ECHO: Prune to act, trace to learn with selective turn memory in agentic RL
The paper proposes ECHO, a selective turn-memory framework for long-horizon language agents. ECHO aims to address the issues of history collapse and traceable learning by compressing completed environment turns into…
ECHO: Prune to act, trace to learn with selective turn memory in agentic RL
Researchers propose ECHO, a selective turn-memory framework to address limitations of existing context management methods in long-horizon language agents. ECHO compresses completed environment turns into compact memory…
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…
FARS: A Fully Automated Research System Deployed at Scale
FARS is a fully automated AI-for-AI research system that can generate, execute, and write complete research papers on various topics at scale. In its first public deployment, FARS produced 166 research papers across 67…
FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning
The paper introduces FedXDS, a method that uses explainable AI (XAI) to help mitigate performance degradation in federated learning caused by statistical heterogeneity between client data distributions. The approach…
FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents
Researchers introduce FinPersona-Bench, a simulation benchmark to measure Mandate Salience Decay (MSD) in autonomous financial agents. MSD refers to the gradual loss of behavioral influence of initial mandates over…
FLARE-AI: Flaw Reporting for AI
Flare-AI is an open-source system designed for reporting issues in AI systems. It aims to streamline the process of flaw reporting by collecting relevant information through conditional logic and early classification…
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…
Freeform Preference Learning for Robotic Manipulation
Researchers introduce Freeform Preference Learning (FPL), a method for training robotic policies based on natural-language preferences provided by humans, rather than binary labels. The method uses the preferences to…
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…
Harnessing Textual Refusal Directions for Multimodal Safety
Researchers propose a new approach called Modality-Agnostic Refusal Steering (MARS) to improve safety in Multimodal Large Language Models without requiring unsafe multimodal data. MARS uses textual refusal directions…
Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision
The study examines how language models (LMs) generate self-explanations for their predictions, and finds that when training LMs to explain which aspects of their inputs influenced their behavior, they often produce…
JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering
Researchers introduce JL1-CC&QA, a new benchmark for remote sensing that extends the JL1-CD dataset with two annotation layers: change captioning (CC) and change question answering (QA). The benchmark includes 5,000…
MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments
The research paper introduces MECoBench, a benchmark for evaluating the collaboration abilities of multimodal agents in visually grounded environments. The study explores three key findings: collaboration generally…
MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments
The paper introduces MECoBench, a new system for testing the collaboration abilities of multimodal large language models in visually grounded environments. The authors conduct extensive experiments with various MLLMs…
Page 38 of 47
