{"total":30,"rows":[{"id":"2403.08715","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","created":"2024-03-13","cited_by_count":93,"area":"agents"},{"id":"2506.15740","title":"SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents","created":"2025-06-17","cited_by_count":71,"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":"2410.13886","title":"Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents","created":"2024-10-11","cited_by_count":65,"area":"agents"},{"id":"2311.10538","title":"Testing Language Model Agents Safely in the Wild","created":"2023-11-17","cited_by_count":46,"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":"2602.17753","title":"The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems","created":"2026-02-19","cited_by_count":30,"area":"agents"},{"id":"2511.20703","title":"PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach","created":"2025-11-24","cited_by_count":22,"area":"agents"},{"id":"2601.05214","title":"Internal Representations as Indicators of Hallucinations in Agent Tool Selection","created":"2026-01-08","cited_by_count":19,"area":"agents"},{"id":"2602.15198","title":"Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems","created":"2026-02-16","cited_by_count":18,"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":"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":"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":"2605.07990","title":"Tool Calling is Linearly Readable and Steerable in Language Models","created":"2026-05-08","cited_by_count":10,"area":"agents"},{"id":"2404.06750","title":"Frontier AI Ethics: Anticipating and Evaluating the Societal Impacts of Language Model Agents","created":"2024-04-10","cited_by_count":5,"area":"agents"},{"id":"2502.15850","title":"Forecasting Frontier Language Model Agent Capabilities","created":"2025-02-21","cited_by_count":5,"area":"agents"},{"id":"2510.26752","title":"The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy","created":"2025-10-30","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":"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":"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":"2607.26064","title":"The Age of AI Agents Demands A New Scientific Paradigm To Sustain Trustworthy Science","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2511.17621","title":"From Competition to Coordination: Market Making as a Scalable Framework for Safe and Aligned Multi-Agent LLM Systems","created":"2025-11-18","cited_by_count":0,"area":"agents"},{"id":"2603.14531","title":"Emotional Cost Functions for AI Safety: Teaching Agents to Feel the Weight of Irreversible Consequences","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2605.27485","title":"Automating Formal Verification with Agent-Guided Tree Search","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2605.28807","title":"Calibrating Conservatism for Scalable Oversight","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.05256","title":"How Far Did They Go? The Persuasive Tactics of Covert LLM Agents in a Discontinued Field Experiment","created":"2026-06-03","cited_by_count":0,"area":"agents"},{"id":"2606.22495","title":"Grounded Scaling: Why Agentic AI Needs Deterministic Environments","created":"2026-06-21","cited_by_count":0,"area":"agents"},{"id":"2607.18548","title":"Engineering Trustworthy Agentic AI for Critical Systems","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2608.15181","title":"Insurance as AI Risk Infrastructure: A Generative-Agent Simulation of AI Adoption","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"}],"next_cursor":null}