{"total":77,"rows":[{"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":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"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":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2503.05659","title":"A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval","created":"2025-03-07","cited_by_count":33,"area":"agents"},{"id":"2509.23055","title":"Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate","created":"2025-09-27","cited_by_count":29,"area":"agents"},{"id":"2505.24671","title":"Multiple LLM Agents Debate for Equitable Cultural Alignment","created":"2025-05-30","cited_by_count":21,"area":"agents"},{"id":"2508.12538","title":"MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Security","created":"2025-08-18","cited_by_count":21,"area":"agents"},{"id":"2606.09863","title":"From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents","created":"2026-06-01","cited_by_count":15,"area":"agents"},{"id":"2504.03255","title":"Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective","created":"2025-04-04","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":"2604.17139","title":"The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration","created":"2026-04-18","cited_by_count":8,"area":"agents"},{"id":"2510.04860","title":"Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails","created":"2025-10-06","cited_by_count":7,"area":"agents"},{"id":"2602.18710","title":"Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse","created":"2026-02-21","cited_by_count":7,"area":"agents"},{"id":"2604.02668","title":"Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems","created":"2026-04-03","cited_by_count":6,"area":"agents"},{"id":"2505.11584","title":"LLM Agents Are Hypersensitive to Nudges","created":"2025-05-16","cited_by_count":5,"area":"agents"},{"id":"2601.00240","title":"When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents","created":"2026-01-01","cited_by_count":5,"area":"agents"},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2505.22998","title":"LLM Agents for Bargaining with Utility-based Feedback","created":"2025-05-29","cited_by_count":4,"area":"agents"},{"id":"2602.08567","title":"ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems","created":"2026-02-09","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":"2605.12991","title":"Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy","created":"2026-05-13","cited_by_count":3,"area":"agents"},{"id":"2606.02646","title":"The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size","created":"2026-05-31","cited_by_count":3,"area":"agents"},{"id":"2504.03185","title":"Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents","created":"2025-04-04","cited_by_count":2,"area":"agents"},{"id":"2510.10943","title":"The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems","created":"2025-10-13","cited_by_count":2,"area":"agents"},{"id":"2512.07801","title":"Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2512.08104","title":"AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2512.17259","title":"Verifiability-First Agents: Provable Observability and Lightweight Audit Agents for Controlling Autonomous LLM Systems","created":"2025-12-19","cited_by_count":2,"area":"agents"},{"id":"2602.00428","title":"When Agents \"Misremember\" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems","created":"2026-01-31","cited_by_count":2,"area":"agents"},{"id":"2604.00478","title":"The Silicon Mirror: Dynamic Behavioral Gating for Anti-Sycophancy in LLM Agents","created":"2026-04-01","cited_by_count":2,"area":"agents"},{"id":"2605.00914","title":"The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate","created":"2026-04-29","cited_by_count":2,"area":"agents"},{"id":"2605.01329","title":"Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents","created":"2026-05-02","cited_by_count":2,"area":"agents"},{"id":"2606.23195","title":"Memory Contagion: Cross-Temporal Propagation of Evaluator Bias via Agent Memory","created":"2026-06-22","cited_by_count":2,"area":"agents"},{"id":"2608.24569","title":"When \"Must\" Becomes \"Maybe\": Constraint Weakening in LLM Agent Workflows","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2609.17989","title":"Whom Do AI Agents Work For? Role Assignment Induces Sponsorship Bias in LLM Recommenders","created":"2026-09-16","cited_by_count":2,"area":"agents"},{"id":"2512.23518","title":"Single LLM Debate, MoLaCE: Mixture of Latent Concept Experts Against Confirmation Bias","created":"2025-12-29","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":"2603.07202","title":"Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing","created":"2026-03-07","cited_by_count":1,"area":"agents"},{"id":"2604.04157","title":"Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents","created":"2026-04-05","cited_by_count":1,"area":"agents"},{"id":"2604.11477","title":"OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems","created":"2026-04-13","cited_by_count":1,"area":"agents"},{"id":"2604.12116","title":"The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment","created":"2026-04-13","cited_by_count":1,"area":"agents"},{"id":"2605.01750","title":"Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation","created":"2026-05-03","cited_by_count":1,"area":"agents"},{"id":"2605.15207","title":"TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination","created":"2026-05-01","cited_by_count":1,"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":"2606.11456","title":"AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2606.18259","title":"Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2607.01047","title":"Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.21518","title":"Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation","created":"2026-07-23","cited_by_count":1,"area":"agents"},{"id":"2608.23045","title":"From Inertia to Objectivity: Improving Deep Research Agents with Noise Isolation","created":"2026-08-24","cited_by_count":1,"area":"agents"},{"id":"2609.18998","title":"One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMs","created":"2026-07-17","cited_by_count":1,"area":"agents"},{"id":"2609.20211","title":"Silence Is Endorsement: Verification-Status Laundering in LLM Agent Pipelines","created":"2026-07-25","cited_by_count":1,"area":"agents"},{"id":"2609.33495","title":"LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2502.02863","title":"OceanChat: The Effect of Virtual Conversational AI Agents on Sustainable Attitude and Behavior Change","created":"2025-02-05","cited_by_count":0,"area":"agents"},{"id":"2506.02514","title":"To Embody or Not: The Effect Of Embodiment On User Perception Of LLM-based Conversational Agents","created":"2025-06-03","cited_by_count":0,"area":"agents"},{"id":"2602.02598","title":"Social Catalysts, Not Moral Agents: The Illusion of Alignment in LLM Societies","created":"2026-02-01","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":"2603.16744","title":"Nonstandard Errors in AI Agents","created":"2026-03-17","cited_by_count":0,"area":"agents"},{"id":"2604.04341","title":"Implementing surrogate goals for safer bargaining in LLM-based agents","created":"2026-04-06","cited_by_count":0,"area":"agents"},{"id":"2604.26561","title":"Preserving Disagreement: Architectural Heterogeneity and Coherence Validation in Multi-Agent Policy Simulation","created":"2026-04-29","cited_by_count":0,"area":"agents"},{"id":"2605.24755","title":"Automated Detection and Classification of Delusion-related Content in Naturalistic Audio Diaries Using Multi-Agent Language Models","created":"2026-05-23","cited_by_count":0,"area":"agents"},{"id":"2606.00603","title":"Toward Agentic Governance: What Shapes LLM-Agent Intervention in Public Forums?","created":"2026-05-30","cited_by_count":0,"area":"agents"},{"id":"2606.16682","title":"Multimodal Evaluator Preference Collapse: Cross-Modal Coupling in Self-Evolving Agents","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2606.18060","title":"PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience","created":"2026-06-16","cited_by_count":0,"area":"agents"},{"id":"2608.11274","title":"Agent Safety Should Be a Runtime Contract","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.14613","title":"Do LLM Agents Negotiate Rationally? A Mechanism-Design Framework for Verifiable Multi-Agent Interaction over A2A/MCP","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2609.04217","title":"At Equal Inference Cost, Multi-Agent Structure Does Not Beat a Single Frozen Agent","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2609.08016","title":"What Does Multi-Agent LLM Debate Actually Change? A Layered Analysis of Disagreement and Answer Quality","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.13463","title":"Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.19843","title":"A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents","created":"2026-09-17","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"},{"id":"2609.23215","title":"Triggers and Diagnostics for LLM-Based Interpretability Failures in Active Inference Agents","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.28854","title":"Persuaded, Not Informed: Incentive-Misaligned Witnesses Defeat In-Context Grounding","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.33295","title":"TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.35279","title":"Measuring Collapse and Correction in Homogeneous-Panel LLM Debate","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.01508","title":"OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.02654","title":"Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"}],"next_cursor":null}