{"total":66,"rows":[{"id":"2505.22954","title":"Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents","created":"2025-05-29","cited_by_count":356,"area":"agents"},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"area":"agents"},{"id":"2504.04072","title":"Among Us: A Sandbox for Measuring and Detecting Agentic Deception","created":"2025-04-05","cited_by_count":26,"area":"agents"},{"id":"2601.11369","title":"Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs","created":"2026-01-16","cited_by_count":20,"area":"agents"},{"id":"2506.12152","title":"Because we have LLMs, we Can and Should Pursue Agentic Interpretability","created":"2025-06-13","cited_by_count":16,"area":"agents"},{"id":"2602.08235","title":"When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents","created":"2026-02-09","cited_by_count":14,"area":"agents"},{"id":"2603.01608","title":"Evaluating and Understanding Scheming Propensity in LLM Agents","created":"2026-03-02","cited_by_count":14,"area":"agents"},{"id":"2504.03255","title":"Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective","created":"2025-04-04","cited_by_count":13,"area":"agents"},{"id":"2505.17767","title":"Position: The Real Barrier to LLM Agent Usability is Agentic ROI","created":"2025-05-23","cited_by_count":12,"area":"agents"},{"id":"2512.06914","title":"SoK: Trust-Authorization Mismatch in LLM Agent Interactions","created":"2025-12-07","cited_by_count":11,"area":"agents"},{"id":"2506.05296","title":"Control Tax: The Price of Keeping AI in Check","created":"2025-06-05","cited_by_count":10,"area":"agents"},{"id":"2602.08995","title":"When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents","created":"2026-02-09","cited_by_count":8,"area":"agents"},{"id":"2604.15384","title":"LinuxArena: A Control Setting for AI Agents in Live Production Software Environments","created":"2026-04-16","cited_by_count":8,"area":"agents"},{"id":"2510.04860","title":"Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails","created":"2025-10-06","cited_by_count":7,"area":"agents"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2504.13707","title":"OpenDeception: Learning Deception and Trust in Human-AI Interaction via Multi-Agent Simulation","created":"2025-04-18","cited_by_count":5,"area":"agents"},{"id":"2605.16282","title":"Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2605.27593","title":"Voluntary Collusion with Secret Tools in Competing LLM Agents","created":"2026-05-26","cited_by_count":4,"area":"agents"},{"id":"2606.05647","title":"Coding with \"Enemy\": Can Human Developers Detect AI Agent Sabotage?","created":"2026-06-04","cited_by_count":4,"area":"agents"},{"id":"2601.23211","title":"Multi-Agent Systems Should be Treated as Principal-Agent Problems","created":"2026-01-30","cited_by_count":3,"area":"agents"},{"id":"2602.16943","title":"Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents","created":"2026-02-18","cited_by_count":3,"area":"agents"},{"id":"2604.03121","title":"An Independent Safety Evaluation of Kimi K2.5","created":"2026-04-03","cited_by_count":3,"area":"agents"},{"id":"2605.06490","title":"Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2505.02709","title":"Technical Report: Evaluating Goal Drift in Language Model Agents","created":"2025-05-05","cited_by_count":2,"area":"agents"},{"id":"2510.22462","title":"Learning \"Partner-Aware\" Collaborators in Multi-Party Collaboration","created":"2025-10-26","cited_by_count":2,"area":"agents"},{"id":"2604.04561","title":"Mapping the Exploitation Surface: A 10,000-Trial Taxonomy of What Makes LLM Agents Exploit Vulnerabilities","created":"2026-04-06","cited_by_count":2,"area":"agents"},{"id":"2604.15236","title":"Agentic Microphysics: A Manifesto for Generative AI Safety","created":"2026-04-16","cited_by_count":2,"area":"agents"},{"id":"2606.30449","title":"Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring","created":"2026-06-29","cited_by_count":2,"area":"agents"},{"id":"2607.10750","title":"Filtering Harmful Actions Isn't Enough: Phantom Transfer in Agentic SDF","created":"2026-07-12","cited_by_count":2,"area":"agents"},{"id":"2608.14825","title":"Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce","created":"2026-08-14","cited_by_count":2,"area":"agents"},{"id":"2608.26372","title":"Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2609.28614","title":"Reward Hacking Challenges Oversight of Autonomous Research Agents","created":"2026-09-23","cited_by_count":2,"area":"agents"},{"id":"2602.05183","title":"Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning","created":"2026-02-05","cited_by_count":1,"area":"agents"},{"id":"2604.02500","title":"I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime","created":"2026-04-02","cited_by_count":1,"area":"agents"},{"id":"2604.17502","title":"Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs","created":"2026-04-19","cited_by_count":1,"area":"agents"},{"id":"2604.22971","title":"Peer Identity Bias in Multi-Agent LLM Evaluation: An Empirical Study Using the TRUST Democratic Discourse Analysis Pipeline","created":"2026-04-24","cited_by_count":1,"area":"agents"},{"id":"2604.23646","title":"Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers Architecture","created":"2026-04-26","cited_by_count":1,"area":"agents"},{"id":"2605.19035","title":"Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On","created":"2026-05-18","cited_by_count":1,"area":"agents"},{"id":"2607.01047","title":"Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.21518","title":"Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation","created":"2026-07-23","cited_by_count":1,"area":"agents"},{"id":"2607.22445","title":"Dynamic Capability Scoping for Enterprise AI Agents: A Synthetic Dataset and Three-Source Permission Architecture","created":"2026-07-24","cited_by_count":1,"area":"agents"},{"id":"2607.25379","title":"Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response","created":"2026-07-28","cited_by_count":1,"area":"agents"},{"id":"2609.39050","title":"Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2509.06701","title":"Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks","created":"2025-09-08","cited_by_count":0,"area":"agents"},{"id":"2509.13356","title":"CogniAlign: Survivability-Grounded Multi-Agent Moral Reasoning for Safe and Transparent AI","created":"2025-09-14","cited_by_count":0,"area":"agents"},{"id":"2601.15630","title":"Agentic AI Governance and Lifecycle Management in Healthcare","created":"2026-01-22","cited_by_count":0,"area":"agents"},{"id":"2603.07848","title":"Intentional Deception as Controllable Capability in LLM Agents","created":"2026-03-08","cited_by_count":0,"area":"agents"},{"id":"2603.13791","title":"DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents","created":"2026-03-14","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":"2604.25067","title":"Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver","created":"2026-04-27","cited_by_count":0,"area":"agents"},{"id":"2606.31046","title":"OpenLife: Toward Open-World Artificial Life with Autonomous LLM Agents","created":"2026-06-30","cited_by_count":0,"area":"agents"},{"id":"2607.05132","title":"When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.14285","title":"ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2608.11274","title":"Agent Safety Should Be a Runtime Contract","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.15304","title":"Understanding Cognition-Induced Risks in Agentic AI Systems","created":"2026-08-15","cited_by_count":0,"area":"agents"},{"id":"2609.08126","title":"SchemeArena: Factorized Stress Testing of Scheming in LLM Agents","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.15494","title":"The Troy Moment: How LLM Agents Adjudicate the Decision Point Under Impossible Tasks, Claimed Authority, and Peer Information","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.18460","title":"Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.23894","title":"Connecting the Dots in Agentic AI Security: A Cross-Dimensional Threat Taxonomy, Evaluation Maturity, and Open Challenges","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.27994","title":"Compliant with Local Controls, Collectively Discriminatory. A Governance Architecture for Multi-Agent AI in Regulated Finance","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2610.04083","title":"Self-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04246","title":"Benchmarking Psychological Dynamics in Generative Agents","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.05793","title":"Topology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent System","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.11351","title":"Deception by Omission: Language Models Knowingly Hide Their Mistakes","created":"2026-10-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}