{"total":81,"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":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531,"area":"agents"},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429,"area":"agents"},{"id":"2501.17315","title":"A sketch of an AI control safety case","created":"2025-01-28","cited_by_count":39,"area":"agents"},{"id":"2505.12923","title":"The Traitors: Deception and Trust in Multi-Agent Language Model Simulations","created":"2025-05-19","cited_by_count":34,"area":"agents"},{"id":"2502.06472","title":"KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment","created":"2025-02-10","cited_by_count":27,"area":"agents"},{"id":"2411.00053","title":"ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration","created":"2024-10-30","cited_by_count":24,"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":"2508.02994","title":"When AIs Judge AIs: The Rise of Agent-as-a-Judge Evaluation for LLMs","created":"2025-08-05","cited_by_count":17,"area":"agents"},{"id":"2601.04583","title":"Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries","created":"2026-01-08","cited_by_count":13,"area":"agents"},{"id":"2504.00374","title":"When Persuasion Overrides Truth in Multi-Agent LLM Debates: Introducing a Confidence-Weighted Persuasion Override Rate (CW-POR)","created":"2025-04-01","cited_by_count":12,"area":"agents"},{"id":"2506.05296","title":"Control Tax: The Price of Keeping AI in Check","created":"2025-06-05","cited_by_count":10,"area":"agents"},{"id":"2510.08240","title":"The Alignment Waltz: Jointly Training Agents to Collaborate for Safety","created":"2025-10-09","cited_by_count":10,"area":"agents"},{"id":"2504.05358","title":"Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction","created":"2025-04-07","cited_by_count":9,"area":"agents"},{"id":"2509.26100","title":"AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models","created":"2025-09-30","cited_by_count":9,"area":"agents"},{"id":"2602.06948","title":"Agentic Uncertainty Reveals Agentic Overconfidence","created":"2026-02-06","cited_by_count":9,"area":"agents"},{"id":"2606.08960","title":"Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops","created":"2026-06-08","cited_by_count":9,"area":"agents"},{"id":"2502.01714","title":"Position: Towards a Responsible LLM-empowered Multi-Agent Systems","created":"2025-02-03","cited_by_count":8,"area":"agents"},{"id":"2506.12482","title":"Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety","created":"2025-06-14","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":"2510.14008","title":"Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment","created":"2025-10-15","cited_by_count":7,"area":"agents"},{"id":"2509.24380","title":"Agentic Services Computing","created":"2025-09-29","cited_by_count":6,"area":"agents"},{"id":"2512.00520","title":"Toward a Safe Internet of Agents","created":"2025-11-29","cited_by_count":6,"area":"agents"},{"id":"2602.15039","title":"GRACE: an Agentic AI for Particle Physics Experiment Design and Simulation","created":"2026-01-31","cited_by_count":6,"area":"agents"},{"id":"2605.15377","title":"Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"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":"2601.17311","title":"Phase Transition for Budgeted Multi-Agent Synergy","created":"2026-01-24","cited_by_count":4,"area":"agents"},{"id":"2605.27628","title":"Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems","created":"2026-05-26","cited_by_count":4,"area":"agents"},{"id":"2607.25152","title":"When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops","created":"2026-07-27","cited_by_count":4,"area":"agents"},{"id":"2506.02539","title":"VerificAgent: Domain-Specific Memory Verification for Scalable Oversight of Aligned Computer-Use Agents","created":"2025-06-03","cited_by_count":3,"area":"agents"},{"id":"2510.10002","title":"Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate","created":"2025-10-11","cited_by_count":3,"area":"agents"},{"id":"2510.26752","title":"The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy","created":"2025-10-30","cited_by_count":3,"area":"agents"},{"id":"2512.03097","title":"Many-to-One Adversarial Consensus: Exposing Multi-Agent Collusion Risks in AI-Based Healthcare","created":"2025-12-01","cited_by_count":3,"area":"agents"},{"id":"2602.00953","title":"SAGE: Agentic Framework for Interpretable and Clinically Translatable Computational Pathology Biomarker Discovery","created":"2026-02-01","cited_by_count":3,"area":"agents"},{"id":"2604.25847","title":"From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling","created":"2026-04-28","cited_by_count":3,"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":"2608.08311","title":"Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution","created":"2026-08-08","cited_by_count":3,"area":"agents"},{"id":"2609.02246","title":"LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"id":"2601.15077","title":"Multi-Agent Constraint Factorization Reveals Latent Invariant Solution Structure","created":"2026-01-21","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":"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":"2604.03201","title":"Coupled Control, Structured Memory, and Verifiable Action in Agentic AI (SCRAT -- Stochastic Control with Retrieval and Auditable Trajectories): A Comparative Perspective from Squirrel Locomotion and Scatter-Hoarding","created":"2026-04-03","cited_by_count":1,"area":"agents"},{"id":"2604.23646","title":"Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers Architecture","created":"2026-04-26","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":"2606.31023","title":"Certified Speculative Execution for Untrusted AI Agents","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2607.07695","title":"Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety","created":"2026-07-08","cited_by_count":1,"area":"agents"},{"id":"2608.25937","title":"Candidate supply and answer selection shape the value of LLM judging in multi-agent systems","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2609.11957","title":"Look Before You Leap: Pre-Action Verification for LLM Agents","created":"2026-08-09","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":"2610.01023","title":"Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents","created":"2026-10-01","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":"2509.13356","title":"CogniAlign: Survivability-Grounded Multi-Agent Moral Reasoning for Safe and Transparent AI","created":"2025-09-14","cited_by_count":0,"area":"agents"},{"id":"2510.25850","title":"Debate2Create: Robot Co-design via Multi-Agent LLM Debate","created":"2025-10-29","cited_by_count":0,"area":"agents"},{"id":"2511.17621","title":"From Competition to Coordination: Market Making as a Scalable Framework for Safe and Aligned Multi-Agent LLM Systems","created":"2025-11-18","cited_by_count":0,"area":"agents"},{"id":"2604.13705","title":"Beyond Arrow's Impossibility: Fairness as an Emergent Property of Multi-Agent Collaboration","created":"2026-04-15","cited_by_count":0,"area":"agents"},{"id":"2604.19049","title":"Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery","created":"2026-04-21","cited_by_count":0,"area":"agents"},{"id":"2605.10397","title":"AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation","created":"2026-05-11","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":"2606.00939","title":"FinCom: A Financial Multi-Agent Demo with Disagree-or-Commit Deliberation","created":"2026-05-31","cited_by_count":0,"area":"agents"},{"id":"2606.02866","title":"When Helping Hurts and How to Fix It: Multi-Agent Debate for Data Cleaning","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"id":"2606.10747","title":"The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2606.24783","title":"Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-Commerce","created":"2026-06-23","cited_by_count":0,"area":"agents"},{"id":"2607.06608","title":"Security and Privacy in Agentic AI: Grand Challenges and Future Directions","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2607.29405","title":"Beyond Component Testing: Validating Agentic AI Systems","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2608.03910","title":"Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social Theory","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.19002","title":"A Theory of Post-hoc Debate Judgement","created":"2026-08-19","cited_by_count":0,"area":"agents"},{"id":"2608.20777","title":"Tree-of-Concerns: Hierarchical Multi-Agent Debate for Unstated-Limitation Extraction in Scientific Critique","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.27141","title":"Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.05069","title":"A Structured Debate-Mixture-of-Agents Framework for Complex Clinical Diagnostic Decision Support","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.07395","title":"Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study","created":"2026-09-07","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":"2609.15293","title":"Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World Failures","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.22712","title":"Trustworthy Agentic AI: Failure Modes, Mitigation Strategies, and a Lifecycle Framework for Autonomous LLM Systems","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.32361","title":"Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.32379","title":"Measurement Boundaries in LLM Financial Agent Evaluation: Fixed-Tape Execution and Multi-Defect Auditing","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.39297","title":"MiniRep: Robust Reputation-Based Aggregation for Multi-Agent Debate","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00972","title":"VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.10611","title":"Verification and Self-Improvement in Agentic AI: Foundations and Limits","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.15924","title":"Scalable Weak-to-Strong Verifier Hardening for Agent Environments","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.19591","title":"L3M: A Verifiable Harness and Runtime for Self-Extending and Self-Improving Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}