All notes, newest first
2,343 notes. Notes 751 to 800, page 16 of 47.
SCOPE: Supply-Chain Operations through Coupled Policies for End-to-End Coordination
The paper proposes a new composite policy model called SCOPE for coordinating decisions in supply chains. Instead of handling decisions separately by different departments and systems, SCOPE combines them into a…
Selective Credibility-Limited Belief Update
The paper introduces a new method called Selective Credibility-Limited Belief Update. This method allows an agent to update its beliefs based on changes in the world, by transforming the epistemic input (information)…
Selective Credibility-Limited Belief Update
The paper introduces a new method for belief update called Selective Credibility-Limited Belief Update. This method allows for partial incorporation of an epistemic input (information) from a source world, addressing a…
Selective Credibility-Limited Belief Update
The paper introduces a new method for updating an agent's beliefs called Selective Credibility-Limited Belief Update. This method allows for partial incorporation of epistemic inputs, meaning only part of a compound…
TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval
Researchers have developed a new method called TCA-SIR for AI to generate scientific hypotheses by learning target-conditioned abstractions (TCAs). This method improves upon previous methods by specifically extracting…
TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval
In this paper, the authors propose a new method called TCA-SIR (Target-Conditioned Abstraction for Scientific Inspiration Retrieval) to help AI generate scientific hypotheses more effectively. The method focuses on…
TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval
Researchers developed a new method called TCA-SIR for AI to generate scientific hypotheses. This method focuses on transferable abstract principles rather than topical similarity when retrieving inspirations for a…
Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
The paper introduces Tycho, a system that constructs and uses game-specific models during interaction to solve complex games as part of the ARC-AGI-3 project. The system separates actionable observations from…
Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
The paper introduces Tycho, a system that helps an artificial agent learn the rules and goals of unfamiliar games. The system separates actionable observations from other frames and uses them to construct game-specific…
Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
The research paper introduces Tycho, a system that helps an agent interact with and understand unfamiliar games by constructing game-specific models during the gameplay. The system separates actionable observations…
When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence
The study presents a framework to quantify and address Derived-Feature Over-Trust (DFOT), which occurs when large language models (LLMs) misuse derived measurements as if they were direct facts. The researchers use…
When Specifications Conflict: A Symmetry-Based Framework for Measuring LLM Preferences
The researchers propose a framework to analyze how large language models (LLMs) handle conflicting specifications when integrating multiple sources of information. They compare four types of representation: pure…
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…
AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching
Researchers have introduced a new framework for ontology matching called AgentMap. This framework can simultaneously discover both equivalent and subsuming mappings in ontologies, which existing systems cannot do. The…
AI as Friction for Reflection Support in Ideation
The authors argue that AI tools designed to remove friction from creative work might not be beneficial as they overlook an important aspect of design ideation: reflection-in-action. The authors suggest that AI should…
AI as Friction for Reflection Support in Ideation
The authors suggest that AI tools used for creative work, designed to reduce friction, may not be ideal as they overlook an essential aspect of the design process: reflection-in-action during ideation. They propose…
Anatomy Contextualized Adaption of CT Foundation Models
Researchers present Anatomy Contextualized Adaptation (ACA), a framework that modifies pre-trained CT foundation models for improved anatomy-level vision-language alignment while maintaining the global context of…
Automated Multilabel Mpox Research Classification with Explainable Transformer Models
A study published in 2026 on arXiv focuses on using AI models, specifically BERT, to classify Mpox research articles into key topics such as outbreaks, vaccination, and epidemiology. BERT was found to perform well…
BayesAME: Bayesian Active Model Evaluation
BayesAME is a new Bayesian framework designed to automatically determine the optimal size of a coreset (a subset of items for evaluating large generative models). This method improves upon existing ones by modeling…
BioVLN: A Simulation Platform for Visual Language Navigation in Biomedical Laboratories
Researchers have developed a simulation platform named BioVLN for navigating robotics in biomedical laboratories. The platform focuses on finding the correct position to approach instruments, ensuring safety by…
BioVLN: A Simulation Platform for Visual Language Navigation in Biomedical Laboratories
Researchers have developed a simulation platform called BioVLN for creating and evaluating visual-language navigation agents in biomedical laboratories. The platform represents each instrument with three regions…
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…
Can AI agents conduct open-ended AI research? Early evidence from two case studies
In a study, two unpublished AI research papers were given to AI agents for completion. Despite the agents completing the engineering tasks without human help, they failed to make significant progress towards answering…
Can AI agents conduct open-ended AI research? Early evidence from two case studies
Two case studies show that current AI agents struggle to make substantial progress towards answering open-ended research questions in AI, even with six days and significant computing resources.
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…
Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM
Researchers have developed a method to evaluate if latent channels in large language models effectively communicate task-relevant information in multi-agent systems. The study applies this method to Qwen3 and Qwen3-8B…
Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM
Researchers introduce a method to study how latent channels in multi-agent systems, which transmit information without using text, impact the receiver's performance. They apply this method to Qwen3-4B and Qwen3-8B on…
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…
From Representations to Behaviors: Exploring the Person-Situation-Behavior Triad in LLMs
The paper presents a framework for analyzing personality-related representations in Language Models (LLMs). The authors adapt Funder's personality triad framework to LLM analysis: Person as internal personality…
Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detection
Researchers propose VulAgentRL, a framework for interprocedural vulnerability detection using agentic reinforcement learning (RL) and a Code Property Graph (CPG). The CPG verifies the evidence cited by the policy…
Human diversity fuels collective creativity that large language models cannot simulate or sustain
Researchers found that diversity among human groups contributes to collective creativity, and this can't be replicated by current AI models. The study compared human creators using their native languages (L1) and…
Improving Item Discoverability in e-Commerce Search via Related Intent Generation
Researchers propose a new system for improving item discoverability in e-commerce searches. The system uses intent-conditioned recall expansion to generate implicit user intents, which helps to expand candidate recall…
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…
Linguistic Monoculture in LLM-Assisted Language Use
The paper discusses the potential impact of using large language models (LLMs) in writing and communication on linguistic diversity. It presents a mathematical framework to analyze how authors and LLMs evolve through…
Linguistic Monoculture in LLM-Assisted Language Use
The study discusses the potential effects of relying on large language models (LLMs) for writing and communication. It suggests that widespread use could lead to a decrease in linguistic variety, a phenomenon referred…
MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
MemSecBench is a new benchmark for testing the lifecycle security of agent memory systems. The benchmark contains 310 cases drawn from various contexts, and it follows a controlled protocol to test the persistence…
MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
Researchers have developed a benchmark called MemSecBench to evaluate the lifecycle security of agent memory systems. The benchmark contains 310 cases from various contexts, each following a specific protocol and using…
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…
OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
Researchers have developed a new benchmark called OmegaUse-OfficeVal to test the performance of large language model (LLM) agents in completing long-horizon office-suite tasks. The benchmark includes 100 tasks that…
On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment
A research paper proposes a novel method called Routing-based On-Policy Distillation (ROPD) to improve the safety of large language models (LLMs). The current fine-tuning approach has a vulnerability where harmful…
Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
Researchers introduce a new method called CE-CM (Capability Estimation via Contextual Models) to help autonomous agents collaborate effectively with novel and diverse partners in a multi-task setting. The method infers…
Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
Researchers propose an approach called CE-CM (Capability Estimation via Contextual Models) to help autonomous agents collaborate with diverse partners in a multi-task setting. The method infers task-invariant…
Progressive Multimodal Alignment for Continual Instruction Tuning
The paper introduces Progressive Multimodal Alignment (PMA), a framework that addresses the issue of projector-level forgetting in Multimodal Continual Instruction Tuning (MCIT). PMA allows the projector to adapt…
Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting
The researchers propose SkillBoost, a framework to help large language models accumulate and reuse experience from past interactions more effectively in real-world applications. The framework mitigates overfitting…
Scientific Knowledge Discovery in the Age of Large Language Models
This research paper reviews 34 peer-reviewed studies that use generative large language models (LLMs) for literature retrieval and screening of candidate studies against eligibility criteria. The study identifies these…
SciFigAlign: Scoring Scientific Figures by Fine-tuned Alignment of Visuals with Manuscript Evidence
Researchers have introduced SciFigAlign, a system for scoring scientific figures based on their ability to support the claims made in the manuscript they're part of. The system uses a dataset of over 3,000 figures from…
SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context
Researchers have created SciFigQual-Bench, a new benchmark for evaluating the quality of scientific figures in computer science papers. The benchmark assesses five dimensions: clarity, layout, caption fit, context…
Page 16 of 47
