{"total":55,"rows":[{"id":"2507.05246","title":"When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors","created":"2025-07-07","cited_by_count":88,"area":"lr"},{"id":"2506.01926","title":"Large language models can learn and generalize steganographic chain-of-thought under process supervision","created":"2025-06-02","cited_by_count":32,"area":"lr"},{"id":"2601.11369","title":"Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs","created":"2026-01-16","cited_by_count":20,"area":"agents"},{"id":"2501.13011","title":"MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking","created":"2025-01-22","cited_by_count":19,"area":"alignment"},{"id":"2601.01685","title":"Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage","created":"2026-01-04","cited_by_count":19,"area":"lr"},{"id":"2602.15198","title":"Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems","created":"2026-02-16","cited_by_count":18,"area":"agents"},{"id":"2606.07157","title":"Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models","created":"2026-06-05","cited_by_count":12,"area":"lr"},{"id":"2507.01413","title":"Evaluating LLM Agent Collusion in Double Auctions","created":"2025-07-02","cited_by_count":11,"area":"agents"},{"id":"2507.14660","title":"When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems","created":"2025-07-19","cited_by_count":11,"area":null},{"id":"2505.03439","title":"The Steganographic Potentials of Language Models","created":"2025-05-06","cited_by_count":10,"area":"lr"},{"id":"2506.05296","title":"Control Tax: The Price of Keeping AI in Check","created":"2025-06-05","cited_by_count":10,"area":"agents"},{"id":"2602.18297","title":"Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory","created":"2026-02-20","cited_by_count":10,"area":"lr"},{"id":"2505.20118","title":"TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2510.27338","title":"Reasoning Models Sometimes Output Illegible Chains of Thought","created":"2025-10-31","cited_by_count":9,"area":"lr"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2511.06448","title":"When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms","created":"2025-11-09","cited_by_count":8,"area":"agents"},{"id":"2602.23163","title":"A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2604.01151","title":"Detecting Multi-Agent Collusion Through Multi-Agent Interpretability","created":"2026-04-01","cited_by_count":7,"area":"agents"},{"id":"2602.08563","title":"Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs","created":"2026-02-09","cited_by_count":6,"area":"safety"},{"id":"2606.04071","title":"Covert Influence Between Language Models","created":"2026-06-02","cited_by_count":6,"area":null},{"id":"2505.19806","title":"Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2507.12872","title":"Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework","created":"2025-07-17","cited_by_count":5,"area":null},{"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":"2607.07368","title":"Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors","created":"2026-07-08","cited_by_count":5,"area":null},{"id":"2607.22925","title":"Not All LLM Reasoning is Visible in the Chain-of-Thought","created":"2026-07-24","cited_by_count":5,"area":"lr"},{"id":"2512.01222","title":"Unsupervised decoding of encoded reasoning using language model interpretability","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2601.00360","title":"Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems","created":"2026-01-01","cited_by_count":4,"area":null},{"id":"2506.17846","title":"Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)","created":"2025-06-21","cited_by_count":3,"area":null},{"id":"2507.03010","title":"Subversion via Focal Points: Investigating Collusion in LLM Monitoring","created":"2025-07-02","cited_by_count":3,"area":"safety"},{"id":"2604.23459","title":"Architecture Matters for Multi-Agent Security","created":"2026-04-25","cited_by_count":3,"area":null},{"id":"2510.19476","title":"A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring","created":"2025-10-22","cited_by_count":2,"area":"lr"},{"id":"2511.09493","title":"Consensus Sampling for Safer Generative AI","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2601.20641","title":"Investigating the Development of Task-Oriented Communication in Vision-Language Models","created":"2026-01-28","cited_by_count":2,"area":"mllm"},{"id":"2603.08104","title":"Invisible Safety Threat: Malicious Finetuning for LLM via Steganography","created":"2026-03-09","cited_by_count":2,"area":"alignment"},{"id":"2608.02698","title":"Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach","created":"2026-08-03","cited_by_count":2,"area":"agents"},{"id":"2609.24967","title":"Emergent Collusion in Long-Horizon LLM Agent Interaction","created":"2026-09-21","cited_by_count":2,"area":"agents"},{"id":"2511.00554","title":"Red-teaming Activation Probes using Prompted LLMs","created":"2025-11-01","cited_by_count":1,"area":"safety"},{"id":"2606.09135","title":"Steganography Without Modification: Hidden Communication via LLM Seeds","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.09931","title":"A Note on the Strategic Confinement Problem","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2609.00595","title":"SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems","created":"2026-09-01","cited_by_count":1,"area":"agents"},{"id":"2609.01491","title":"GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions","created":"2026-09-01","cited_by_count":1,"area":"agents"},{"id":"2609.32701","title":"Despite Instructions: Frontier Agents Improvise Covert Channels at Test Time","created":"2026-09-26","cited_by_count":1,"area":"agents"},{"id":"2609.39050","title":"Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2508.13326","title":"Decoding Communications with Partial Information","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2512.13821","title":"The Double Life of Code World Models: Provably Unmasking Malicious Behavior Through Execution Traces","created":"2025-12-15","cited_by_count":0,"area":"wm"},{"id":"2602.14095","title":"NEST: Nascent Encoded Steganographic Thoughts","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2608.14697","title":"Synchronized Logit Steering: Real-world Steganography","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2609.03035","title":"You Can't Escape Your Own Activations : Evaluation Awareness and Multi-Agent Monitoring","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.06140","title":"Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.28900","title":"Codetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusion","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.30048","title":"Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.31121","title":"Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.35402","title":"Persistent Partners Raise Prices Among Learning Agents","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39838","title":"Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.03033","title":"When Numbers Start Talking: Numerical Signalling and Strategic Behaviour Among LLMs","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}