{"total":45,"rows":[{"id":"2507.14805","title":"Subliminal Learning: Language models transmit behavioral traits via hidden signals in data","created":"2025-07-20","cited_by_count":95,"area":null},{"id":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53,"area":null},{"id":"2502.04510","title":"Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems","created":"2025-02-06","cited_by_count":23,"area":null},{"id":"2505.19212","title":"When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas","created":"2025-05-25","cited_by_count":15,"area":null},{"id":"2512.16856","title":"Distributional AGI Safety","created":"2025-12-18","cited_by_count":12,"area":null},{"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":"2502.06470","title":"A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2509.20393","title":"The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind","created":"2025-09-23","cited_by_count":8,"area":null},{"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":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"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":"2510.12826","title":"Scheming Ability in LLM-to-LLM Strategic Interactions","created":"2025-10-11","cited_by_count":5,"area":null},{"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":"2601.00360","title":"Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems","created":"2026-01-01","cited_by_count":4,"area":null},{"id":"2603.25100","title":"From Logic Monopoly to Social Contract: Separation of Power and the Institutional Foundations for Autonomous Agent Economies","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2604.07007","title":"AgentCity: Constitutional Governance for Autonomous Agent Economies via Separation of Power","created":"2026-04-08","cited_by_count":3,"area":null},{"id":"2604.23459","title":"Architecture Matters for Multi-Agent Security","created":"2026-04-25","cited_by_count":3,"area":null},{"id":"2608.16347","title":"Architecture-Dependent Causal Transfer of Activation States Across Large Language Models","created":"2026-08-17","cited_by_count":3,"area":null},{"id":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2511.09493","title":"Consensus Sampling for Safer Generative AI","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2607.04432","title":"Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2609.09150","title":"Copying explains the collective behavior of AI agents in the wild","created":"2026-09-08","cited_by_count":2,"area":null},{"id":"2511.21935","title":"Breaking Algorithmic Collusion in Human-AI Ecosystems","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2603.15655","title":"Beyond Reward Suppression: Reshaping Steganographic Communication Protocols in MARL via Dynamic Representational Circuit Breaking","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2605.06738","title":"Trust Without Trusting: A Recomputable Trust Protocol for Autonomous Agents","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.29062","title":"Bosses, Kings, and the Commons: Cooperation Under Power Asymmetry in LLM Societies","created":"2026-05-27","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":"2606.29389","title":"Exploring the Cryptographic Limits of Transformer Networks","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2508.13326","title":"Decoding Communications with Partial Information","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2511.21779","title":"Aligning Artificial Superintelligence via a Multi-Box Protocol","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2511.21802","title":"Tacit Bidder-Side Collusion: Artificial Intelligence in Dynamic Auctions","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2605.19270","title":"DECOR: Auditing LLM Deception via Information Manipulation Theory","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.27586","title":"You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2608.22512","title":"HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.00519","title":"The Safeguard Worked. Is the LLM System Safer?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.05591","title":"WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent Societies","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.06140","title":"Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.07675","title":"Your Agent Says Yes: Interpreting Adversarial Market Behavior Beyond Individual Transactions","created":"2026-09-07","cited_by_count":0,"area":null},{"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":"2609.33871","title":"Population Physics, Population Problems: Safety and Emergence in LLM Societies","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35402","title":"Persistent Partners Raise Prices Among Learning Agents","created":"2026-09-28","cited_by_count":0,"area":null},{"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},{"id":"2610.11012","title":"Distillation for Incrimination and Distillation for Capabilities","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.19342","title":"Why Do Agent Teams Fail Across Boundaries? A Failure Taxonomy for Agent-to-Agent Systems with Private States","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}