{"total":44,"rows":[{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529,"area":"agents"},{"id":"2312.03664","title":"Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia","created":"2023-12-06","cited_by_count":126,"area":"agents"},{"id":"2408.06361","title":"Large Language Model Agent in Financial Trading: A Survey","created":"2024-07-26","cited_by_count":60,"area":"agents"},{"id":"2409.09013","title":"AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents","created":"2024-09-13","cited_by_count":31,"area":"agents"},{"id":"2506.04018","title":"AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents","created":"2025-06-04","cited_by_count":22,"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":"2604.01151","title":"Detecting Multi-Agent Collusion Through Multi-Agent Interpretability","created":"2026-04-01","cited_by_count":7,"area":"agents"},{"id":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2607.02514","title":"Distributed Attacks in Persistent-State AI Control","created":"2026-07-02","cited_by_count":5,"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":"2605.30322","title":"Gram: Assessing sabotage propensities via automated alignment auditing","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2608.12323","title":"Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2609.20812","title":"Quantifying Overclaiming Propensity in Frontier LLM Agents","created":"2026-09-17","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":"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":"2510.23245","title":"Multi-Stakeholder Alignment in LLM-Powered Collaborative AI Systems: A Multi-Agent Framework for Intelligent Tutoring","created":"2025-10-27","cited_by_count":2,"area":"agents"},{"id":"2603.05872","title":"Evolving Deception: When Agents Evolve, Deception Wins","created":"2026-03-06","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":"2605.10059","title":"Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2605.28114","title":"Language model agents show in-group trust bias invisible to standard behavioural audits","created":"2026-05-27","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":"2602.04197","title":"From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents","created":"2026-02-04","cited_by_count":1,"area":"agents"},{"id":"2603.07202","title":"Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing","created":"2026-03-07","cited_by_count":1,"area":"agents"},{"id":"2604.04157","title":"Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents","created":"2026-04-05","cited_by_count":1,"area":"agents"},{"id":"2605.31445","title":"Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Information","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"id":"2606.02380","title":"SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2607.28330","title":"Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace Agents","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2609.18605","title":"PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?","created":"2026-09-16","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":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2606.10747","title":"The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2606.28456","title":"Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game","created":"2026-06-26","cited_by_count":0,"area":"agents"},{"id":"2607.06608","title":"Security and Privacy in Agentic AI: Grand Challenges and Future Directions","created":"2026-07-07","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":"2608.09574","title":"The Politician, the Liar, and the Obedient Worker: Emerging Behavior of LLM Agents in Hierarchical Games","created":"2026-08-10","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":"2609.05975","title":"Intent Drift at SME Scale: Deployment Practice, Not Model Capability, Determines Agentic Compliance","created":"2026-09-05","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":"2610.06748","title":"BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents","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"},{"id":"2610.17301","title":"The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}