{"total":32,"rows":[{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2402.07510","title":"Secret Collusion among AI Agents: Multi-Agent Deception via Steganography","created":"2024-02-12","cited_by_count":113,"area":"agents"},{"id":"2506.23844","title":"A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents","created":"2025-06-30","cited_by_count":29,"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":"2510.06445","title":"A Survey on Agentic Security: Applications, Threats and Defenses","created":"2025-10-07","cited_by_count":20,"area":"agents"},{"id":"2605.18583","title":"Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks","created":"2026-05-18","cited_by_count":13,"area":"agents"},{"id":"2604.23338","title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","created":"2026-04-25","cited_by_count":11,"area":"agents"},{"id":"2312.01818","title":"Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto","created":"2023-12-04","cited_by_count":7,"area":"agents"},{"id":"2503.03796","title":"Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm","created":"2025-03-05","cited_by_count":6,"area":"agents"},{"id":"2606.28425","title":"Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems","created":"2026-06-25","cited_by_count":5,"area":"agents"},{"id":"2606.15385","title":"Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds","created":"2026-06-13","cited_by_count":4,"area":"agents"},{"id":"2606.28430","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","created":"2026-06-26","cited_by_count":4,"area":"agents"},{"id":"2608.16801","title":"When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding","created":"2026-08-17","cited_by_count":3,"area":"agents"},{"id":"2609.02246","title":"LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"id":"2504.03185","title":"Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents","created":"2025-04-04","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":"2606.11456","title":"AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2607.22188","title":"Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectives","created":"2026-07-24","cited_by_count":1,"area":"agents"},{"id":"2608.06811","title":"Coupling Planning with Episodic Memory in LLM Agents for Software Issue Resolution","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"id":"2608.09855","title":"The Greatness of Science Cannot Be Planned: Agentic Auto-Research is Fuzz Testing","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.13564","title":"Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2608.18081","title":"Position: Behavioral Systems Require Behavioral Tests","created":"2026-05-31","cited_by_count":1,"area":"agents"},{"id":"2609.02889","title":"Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM Agents","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2609.11028","title":"BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure","created":"2026-09-10","cited_by_count":1,"area":"agents"},{"id":"2508.19500","title":"Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills","created":"2025-08-27","cited_by_count":0,"area":"agents"},{"id":"2604.06392","title":"Qualixar OS: A Universal Operating System for AI Agent Orchestration","created":"2026-04-07","cited_by_count":0,"area":"agents"},{"id":"2604.23210","title":"Discovering Agentic Safety Specifications from 1-Bit Danger Signals","created":"2026-04-25","cited_by_count":0,"area":"agents"},{"id":"2608.16207","title":"Competing at Every Price Point with Agentic Evolution over a Menu of LLMs","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2608.17524","title":"Evaluating RL Explainability Methods by How Much They Help Fix Bugs in Agents","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"id":"2608.29460","title":"Can escalation channels redirect reward hacking toward defect disclosure?","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2610.01508","title":"OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.03055","title":"hacktrace: behavior-supervised detection of reward hacking during code generation","created":"2026-10-02","cited_by_count":0,"area":"agents"}],"next_cursor":null}