{"total":77,"rows":[{"id":"2401.10019","title":"R-Judge: Benchmarking Safety Risk Awareness for LLM Agents","created":"2024-01-18","cited_by_count":288,"area":"agents"},{"id":"2406.03679","title":"On the Effects of Data Scale on UI Control Agents","created":"2024-06-06","cited_by_count":194,"area":"agents"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2606.09498","title":"Self-Harness: Harnesses That Improve Themselves","created":"2026-06-08","cited_by_count":107,"area":"agents"},{"id":"2502.08640","title":"Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs","created":"2025-02-12","cited_by_count":67,"area":"agents"},{"id":"2402.11651","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","created":"2024-02-18","cited_by_count":50,"area":"agents"},{"id":"2407.11977","title":"Building Better AI Agents: A Provocation on the Utilisation of Persona in LLM-based Conversational Agents","created":"2024-05-26","cited_by_count":26,"area":"agents"},{"id":"2412.00804","title":"Examining Identity Drift in Conversations of LLM Agents","created":"2024-12-01","cited_by_count":25,"area":"agents"},{"id":"2602.07150","title":"On Randomness in Agentic Evals","created":"2026-02-06","cited_by_count":17,"area":"agents"},{"id":"2510.19107","title":"When Your AI Agent Succumbs to Peer-Pressure: Studying Opinion-Change Dynamics of LLMs","created":"2025-10-21","cited_by_count":16,"area":"agents"},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2604.05149","title":"EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering","created":"2026-04-06","cited_by_count":15,"area":"agents"},{"id":"2602.22953","title":"General Agent Evaluation","created":"2026-02-26","cited_by_count":13,"area":"agents"},{"id":"2410.09114","title":"Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities","created":"2024-10-10","cited_by_count":12,"area":"agents"},{"id":"2502.16690","title":"From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task","created":"2025-02-23","cited_by_count":10,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2509.13588","title":"CoBRA: Programming Cognitive Bias in Social Agents Using Classic Social Science Experiments","created":"2025-09-16","cited_by_count":8,"area":"agents"},{"id":"2602.03664","title":"Mitigating Conversational Inertia in Multi-Turn Agents","created":"2026-02-03","cited_by_count":7,"area":"agents"},{"id":"2602.18710","title":"Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse","created":"2026-02-21","cited_by_count":7,"area":"agents"},{"id":"2508.17094","title":"PowerChain: A Verifiable Agentic AI System for Automating Distribution Grid Analyses","created":"2025-08-23","cited_by_count":6,"area":"agents"},{"id":"2603.20213","title":"AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization","created":"2026-03-02","cited_by_count":6,"area":"agents"},{"id":"2605.21404","title":"What Twelve LLM Agent Benchmark Papers Disclose About Themselves: A Pilot Audit and an Open Scoring Schema","created":"2026-05-20","cited_by_count":6,"area":"agents"},{"id":"2606.11543","title":"SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior","created":"2026-06-10","cited_by_count":6,"area":"agents"},{"id":"2608.11888","title":"Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents","created":"2026-08-12","cited_by_count":6,"area":"agents"},{"id":"2505.11584","title":"LLM Agents Are Hypersensitive to Nudges","created":"2025-05-16","cited_by_count":5,"area":"agents"},{"id":"2605.28840","title":"How Consistent Are LLM Agents? Measuring Behavioral Reproducibility in Multi-Step Tool-Calling Pipelines","created":"2026-04-23","cited_by_count":5,"area":"agents"},{"id":"2410.19920","title":"Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting","created":"2024-10-25","cited_by_count":4,"area":"agents"},{"id":"2509.00482","title":"Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting","created":"2025-08-30","cited_by_count":4,"area":"agents"},{"id":"2510.04695","title":"Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents","created":"2025-10-06","cited_by_count":4,"area":"agents"},{"id":"2507.19543","title":"Agent WARPP: Workflow Adherence via Runtime Parallel Personalization","created":"2025-07-23","cited_by_count":3,"area":"agents"},{"id":"2509.08535","title":"Agents of Discovery","created":"2025-09-10","cited_by_count":3,"area":"agents"},{"id":"2510.06222","title":"Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-Making","created":"2025-08-30","cited_by_count":3,"area":"agents"},{"id":"2510.14453","title":"Natural Language Tools: A Natural Language Approach to Tool Calling In Large Language Agents","created":"2025-10-16","cited_by_count":3,"area":"agents"},{"id":"2602.03238","title":"\"LLM Agent Performance\" Is Not a Single Evaluation Target","created":"2026-02-03","cited_by_count":3,"area":"agents"},{"id":"2605.30723","title":"Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents","created":"2026-05-29","cited_by_count":3,"area":"agents"},{"id":"2605.31408","title":"Skill Availability and Presentation Granularity in Large-Language-Model Agents: A Controlled SkillsBench Study","created":"2026-05-29","cited_by_count":3,"area":"agents"},{"id":"2606.26924","title":"A Deterministic Control Plane for LLM Coding Agents","created":"2026-06-25","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2609.09218","title":"The Double Measurement Confound in Agent Benchmarks: De-Scaffolding, Ground-Truth Scoring, and Reliability Beyond the Mean","created":"2026-09-06","cited_by_count":3,"area":"agents"},{"id":"2609.12205","title":"Plans They Abandon, Reports They Author: The Narrative Layer of Autonomous Agents","created":"2026-09-10","cited_by_count":3,"area":"agents"},{"id":"2601.04716","title":"Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes","created":"2026-01-08","cited_by_count":2,"area":"agents"},{"id":"2602.00685","title":"HumanStudy-Bench: Towards AI Agent Design for Participant Simulation","created":"2026-01-31","cited_by_count":2,"area":"agents"},{"id":"2603.18245","title":"Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety","created":"2026-03-18","cited_by_count":2,"area":"agents"},{"id":"2606.11217","title":"Preregistration for Experiments with AI Agents","created":"2026-05-03","cited_by_count":2,"area":"agents"},{"id":"2606.21140","title":"Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents","created":"2026-06-19","cited_by_count":2,"area":"agents"},{"id":"2610.02267","title":"Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses","created":"2026-10-01","cited_by_count":2,"area":"agents"},{"id":"2503.22719","title":"LLM-based Agent Simulation for Maternal Health Interventions: Uncertainty Estimation and Decision-focused Evaluation","created":"2025-03-25","cited_by_count":1,"area":"agents"},{"id":"2510.25017","title":"StorageXTuner: An LLM Agent-Driven Automatic Tuning Framework for Heterogeneous Storage Systems","created":"2025-10-28","cited_by_count":1,"area":"agents"},{"id":"2605.07830","title":"CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2605.21781","title":"Reflective Prompt Tuning through Language Model Function-Calling","created":"2026-05-20","cited_by_count":1,"area":"agents"},{"id":"2605.26731","title":"It's Not the Capability: Harness Sensitivity Is Non-Monotone Across LLM Agent Tiers","created":"2026-05-26","cited_by_count":1,"area":"agents"},{"id":"2606.18259","title":"Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2606.20978","title":"How Should Agents Read Demonstrations? Hierarchical Structure Beats Flat Action Logs","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2608.06171","title":"Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2608.24361","title":"Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2609.05587","title":"Agents Trust Tools Too Much: Measuring Reliance on Unreliable Tools","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2506.20409","title":"TAPS: Tool-Augmented Personalisation via Structured Tagging","created":"2025-06-25","cited_by_count":0,"area":"agents"},{"id":"2602.05524","title":"AI Agent Systems for Supply Chains: Structured Decision Prompts and Memory Retrieval","created":"2026-02-05","cited_by_count":0,"area":"agents"},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2604.07745","title":"The Cartesian Cut in Agentic AI","created":"2026-04-09","cited_by_count":0,"area":"agents"},{"id":"2604.11655","title":"RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2606.20632","title":"Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behavior","created":"2026-05-30","cited_by_count":0,"area":"agents"},{"id":"2606.26356","title":"Instruction Bleed: Cross-Module Interference in Prompt-Composed Agentic Systems","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2608.03609","title":"Formal Verification of Agentic Systems over Operational Data","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.06968","title":"How a shared state is described determines whether AI agents synchronize","created":"2026-08-07","cited_by_count":0,"area":"agents"},{"id":"2608.22331","title":"Noise Floor Audit for Agent Benchmarks","created":"2026-08-23","cited_by_count":0,"area":"agents"},{"id":"2609.05036","title":"Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.14570","title":"Disentangling Topology and Diversity in Multi-Agent LLMs for Multilingual Low-Resource Emotion Detection","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.14758","title":"Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.16270","title":"Cheap Talk Stabilizes Strategic Interaction in LLM Agents","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.18357","title":"Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.32379","title":"Measurement Boundaries in LLM Financial Agent Evaluation: Fixed-Tape Execution and Multi-Defect Auditing","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33885","title":"Prospective Interpretation Risk: Principled Communication Control Between LLMs","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34971","title":"Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.02413","title":"Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.05367","title":"AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.11678","title":"TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation","created":"2026-10-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}