{"total":13,"rows":[{"id":"2312.11671","title":"Evaluating Language-Model Agents on Realistic Autonomous Tasks","created":"2023-12-18","cited_by_count":96,"area":"agents"},{"id":"2408.12622","title":"The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence","created":"2024-08-14","cited_by_count":16,"area":"agents"},{"id":"2601.12449","title":"AgenTRIM: Tool Risk Mitigation for Agentic AI","created":"2026-01-18","cited_by_count":11,"area":"agents"},{"id":"2509.25302","title":"Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents","created":"2025-09-29","cited_by_count":7,"area":"agents"},{"id":"2603.06874","title":"LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models","created":"2026-03-06","cited_by_count":5,"area":"agents"},{"id":"2604.15559","title":"Subliminal Transfer of Unsafe Behaviors in AI Agent Distillation","created":"2026-04-16","cited_by_count":5,"area":"agents"},{"id":"2601.13981","title":"VirtualCrime: Evaluating the Criminal Potential and Agentic Behaviors of Large Language Models via Sandbox Simulation","created":"2026-01-20","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":"2604.25067","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":"2605.19722","title":"Measuring Safety Alignment Effects in Autonomous Security Agents","created":"2026-05-19","cited_by_count":0,"area":"agents"},{"id":"2607.03423","title":"Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2608.04755","title":"\"Allow\" to Achieve, Over-Privileged Inadvertently: The Unintended Cost of Task-Completion-Driven Pop-up Decisions in Mobile GUI Agents","created":"2026-08-05","cited_by_count":0,"area":"agents"},{"id":"2609.28197","title":"PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety","created":"2026-09-23","cited_by_count":0,"area":"agents"}],"next_cursor":null}