{"total":38,"rows":[{"id":"2410.09024","title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","created":"2024-10-11","cited_by_count":437,"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":"2502.08640","title":"Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs","created":"2025-02-12","cited_by_count":67,"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":"2401.01312","title":"LLM Harmony: Multi-Agent Communication for Problem Solving","created":"2024-01-02","cited_by_count":35,"area":"agents"},{"id":"2501.16173","title":"Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma","created":"2025-01-27","cited_by_count":25,"area":"agents"},{"id":"2512.20798","title":"A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents","created":"2025-12-23","cited_by_count":13,"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":"2503.18825","title":"EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agents","created":"2025-03-24","cited_by_count":10,"area":"agents"},{"id":"2601.08462","title":"M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games","created":"2026-01-13","cited_by_count":8,"area":"agents"},{"id":"2602.16662","title":"Evaluating Collective Behaviour of Hundreds of LLM Agents","created":"2026-02-18","cited_by_count":8,"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":"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":"2404.18978","title":"Towards Generalizable Agents in Text-Based Educational Environments: A Study of Integrating RL with LLMs","created":"2024-04-29","cited_by_count":4,"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":"2512.16167","title":"Ev-Trust: An Evolutionarily Stable Trust Mechanism for Decentralized LLM-Based Multi-Agent Service Economies","created":"2025-12-18","cited_by_count":3,"area":"agents"},{"id":"2604.28093","title":"What Makes a Good Terminal-Agent Benchmark Task: A Guideline for Adversarial, Difficult, and Legible Evaluation Design","created":"2026-04-30","cited_by_count":3,"area":"agents"},{"id":"2605.22643","title":"Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety","created":"2026-05-21","cited_by_count":3,"area":"agents"},{"id":"2506.02946","title":"Abstract Counterfactuals for Language Model Agents","created":"2025-06-03","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":"2603.12564","title":"Sell Me This Stock: Unsafe Recommendation Drift in LLM Agents","created":"2026-03-13","cited_by_count":2,"area":"agents"},{"id":"2603.14975","title":"Why Agents Compromise Safety Under Pressure","created":"2026-03-16","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":"2502.05442","title":"The Odyssey of the Fittest: Can Agents Survive and Still Be Good?","created":"2025-02-08","cited_by_count":1,"area":"agents"},{"id":"2506.13774","title":"Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values","created":"2025-06-08","cited_by_count":1,"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":"2606.07805","title":"Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems","created":"2026-06-05","cited_by_count":1,"area":"agents"},{"id":"2602.05354","title":"Do Web Agents Investigate Before They Decide?","created":"2026-02-05","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":"2603.14987","title":"Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI","created":"2026-03-16","cited_by_count":0,"area":"agents"},{"id":"2605.19351","title":"PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies","created":"2026-05-19","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":"2607.18548","title":"Engineering Trustworthy Agentic AI for Critical Systems","created":"2026-07-20","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":"2609.05995","title":"Agentic Pressure: The Endogenous Entropy of Reliable Autonomy","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.17552","title":"Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks","created":"2026-07-16","cited_by_count":0,"area":"agents"},{"id":"2609.22600","title":"From Certain Doom to Survival: Agent-Driven Self-Governance in LLM Agent Societies","created":"2026-09-18","cited_by_count":0,"area":"agents"}],"next_cursor":null}