{"total":33,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"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":"2510.05179","title":"Agentic Misalignment: How LLMs Could Be Insider Threats","created":"2025-10-05","cited_by_count":158,"area":"agents"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2406.12814","title":"Dissecting Adversarial Robustness of Multimodal LM Agents","created":"2024-06-18","cited_by_count":120,"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":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2603.00829","title":"Constitutional Black-Box Monitoring for Scheming in LLM Agents","created":"2026-02-28","cited_by_count":10,"area":"agents"},{"id":"2505.04345","title":"Build Agent Advocates, Not Platform Agents","created":"2025-05-07","cited_by_count":8,"area":"agents"},{"id":"2506.11083","title":"RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates","created":"2025-06-04","cited_by_count":7,"area":"agents"},{"id":"2603.20320","title":"The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents","created":"2026-03-19","cited_by_count":7,"area":"agents"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2506.22957","title":"Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models","created":"2025-06-28","cited_by_count":5,"area":"agents"},{"id":"2401.03529","title":"Quantifying stability of non-power-seeking in artificial agents","created":"2024-01-07","cited_by_count":2,"area":"agents"},{"id":"2506.02357","title":"Evaluating LLM Agent Adherence to Hierarchical Safety Principles: A Lightweight Benchmark for Probing Foundational Controllability Components","created":"2025-06-03","cited_by_count":2,"area":"agents"},{"id":"2606.03698","title":"Multi$^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2402.05829","title":"Limitations of Agents Simulated by Predictive Models","created":"2024-02-08","cited_by_count":1,"area":"agents"},{"id":"2602.08964","title":"A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents","created":"2026-02-09","cited_by_count":1,"area":"agents"},{"id":"2603.19282","title":"Framing Effects in Independent-Agent Large Language Models: A Cross-Family Behavioral Analysis","created":"2026-03-02","cited_by_count":1,"area":"agents"},{"id":"2604.19752","title":"Soft-Label Governance for Distributional Safety in Multi-Agent Systems","created":"2026-03-19","cited_by_count":1,"area":"agents"},{"id":"2605.09045","title":"Containment Verification: AI Safety Guarantees Independent of Alignment","created":"2026-05-09","cited_by_count":1,"area":"agents"},{"id":"2605.13851","title":"Invisible Orchestrators Suppress Protective Behavior and Dissociate Power-Holders: Safety Risks in Multi-Agent LLM Systems","created":"2026-03-17","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":"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":"2509.06701","title":"Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks","created":"2025-09-08","cited_by_count":0,"area":"agents"},{"id":"2601.00042","title":"Large Empirical Case Study: Go-Explore adapted for AI Red Team Testing","created":"2025-12-31","cited_by_count":0,"area":"agents"},{"id":"2602.20424","title":"Implicit Intelligence -- Evaluating Agents on What Users Don't Say","created":"2026-02-23","cited_by_count":0,"area":"agents"},{"id":"2603.13244","title":"Agentic AI, Retrieval-Augmented Generation, and the Institutional Turn: Legal Architectures and Financial Governance in the Age of Distributional AGI","created":"2026-02-20","cited_by_count":0,"area":"agents"},{"id":"2603.13791","title":"DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents","created":"2026-03-14","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":"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":"2606.22495","title":"Grounded Scaling: Why Agentic AI Needs Deterministic Environments","created":"2026-06-21","cited_by_count":0,"area":"agents"},{"id":"2610.04083","title":"Self-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough","created":"2026-10-02","cited_by_count":0,"area":"agents"}],"next_cursor":null}