{"total":66,"rows":[{"id":"2509.23055","title":"Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate","created":"2025-09-27","cited_by_count":29,"area":"agents"},{"id":"2601.19921","title":"Demystifying Multi-Agent Debate: The Role of Confidence and Diversity","created":"2026-01-09","cited_by_count":18,"area":"lr"},{"id":"2511.02687","title":"The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation","created":"2025-11-04","cited_by_count":13,"area":"agents"},{"id":"2601.10825","title":"Reasoning Models Generate Societies of Thought","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"id":"2510.07593","title":"AgentAsk: Multi-Agent Systems Need to Ask","created":"2025-10-08","cited_by_count":10,"area":"agents"},{"id":"2603.00131","title":"Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"id":"2606.13003","title":"The Illusion of Multi-Agent Advantage","created":"2026-06-11","cited_by_count":9,"area":null},{"id":"2603.26993","title":"On the Reliability Limits of LLM-Based Multi-Agent Planning","created":"2026-03-27","cited_by_count":8,"area":"agents"},{"id":"2604.18005","title":"Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation","created":"2026-04-20","cited_by_count":7,"area":"agents"},{"id":"2606.00820","title":"Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate","created":"2026-05-30","cited_by_count":7,"area":"lr"},{"id":"2601.21464","title":"Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation","created":"2026-01-29","cited_by_count":6,"area":"synth"},{"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":"2511.19417","title":"Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration","created":"2025-11-24","cited_by_count":5,"area":"lr"},{"id":"2601.05746","title":"DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation","created":"2026-01-09","cited_by_count":5,"area":"agents"},{"id":"2603.01221","title":"Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning","created":"2026-03-01","cited_by_count":5,"area":"lr"},{"id":"2603.27404","title":"Heterogeneous Debate Engine: Identity-Grounded Cognitive Architecture for Resilient LLM-Based Ethical Tutoring","created":"2026-03-28","cited_by_count":5,"area":null},{"id":"2510.20963","title":"When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?","created":"2025-10-23","cited_by_count":4,"area":"lr"},{"id":"2606.27409","title":"Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement","created":"2026-06-25","cited_by_count":4,"area":"agents"},{"id":"2510.14453","title":"Natural Language Tools: A Natural Language Approach to Tool Calling In Large Language Agents","created":"2025-10-16","cited_by_count":3,"area":"agents"},{"id":"2605.08647","title":"AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators","created":"2026-05-09","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":"2606.07810","title":"SLMJury: Can Small Language Models Judge as Well as Large Ones?","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2512.07665","title":"Reliable agent engineering should integrate machine-compatible organizational principles","created":"2025-12-08","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":"2605.03310","title":"Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems","created":"2026-05-05","cited_by_count":2,"area":"agents"},{"id":"2609.19124","title":"Flag Game: A Toy Model for Mechanistic Swarm Interpretability","created":"2026-09-16","cited_by_count":2,"area":null},{"id":"2509.21848","title":"Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration","created":"2025-09-26","cited_by_count":1,"area":"agents"},{"id":"2511.08710","title":"Convergence dynamics of Agent-to-Agent Interactions with Misaligned objectives","created":"2025-11-11","cited_by_count":1,"area":"agents"},{"id":"2601.02854","title":"M3MAD-Bench: Multi-Dimensional Evaluation of Multi-Agent Debate Across Domains and Modalities","created":"2026-01-06","cited_by_count":1,"area":"agents"},{"id":"2603.24973","title":"Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulation","created":"2026-03-26","cited_by_count":1,"area":"agents"},{"id":"2605.07646","title":"MAVEN: Multi-Agent Verification-Elaboration Network with In-Step Epistemic Auditing","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.09027","title":"GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives","created":"2026-05-09","cited_by_count":1,"area":"agents"},{"id":"2605.30102","title":"When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems","created":"2026-05-28","cited_by_count":1,"area":"agents"},{"id":"2605.30802","title":"Design and Evaluation of Multi-Agent AI Oracle Systems for Prediction Market Resolution","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"id":"2606.01462","title":"An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models","created":"2026-05-31","cited_by_count":1,"area":"lr"},{"id":"2606.03032","title":"The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2606.10296","title":"The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-Judge","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2606.10307","title":"Early-Token Confidence Predicts Reasoning Quality in Multi-Agent LLM Debate","created":"2026-06-09","cited_by_count":1,"area":"lr"},{"id":"2607.27958","title":"$\\Sigma$-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.03239","title":"Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems","created":"2026-08-04","cited_by_count":1,"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":"2605.02379","title":"Fair Agents: Balancing Multistakeholder Alignment in Multi-Agent Personalization Systems","created":"2026-05-04","cited_by_count":0,"area":"agents"},{"id":"2605.09421","title":"MACAA: Belief-Revision Multi-Agent Reasoning for Code Authorship Verification","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.11789","title":"Beyond Inefficiency: Systemic Costs of Incivility in Multi-Agent Monte Carlo Simulations","created":"2026-05-12","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":"2606.07532","title":"Durable Evaluation Framework: Adversarial Arbitration for Sycophancy Reduction in Large Language Models","created":"2026-04-21","cited_by_count":0,"area":"alignment"},{"id":"2606.13591","title":"Confidence Composition for Multiagent Language Model Systems","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.28166","title":"Tandem Reinforcement Learning with Verifiable Rewards","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2607.01600","title":"BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systems","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.12480","title":"TRACE: An Operational Reasoning Schema for Auditable Agentic Commitments","created":"2026-07-14","cited_by_count":0,"area":"lr"},{"id":"2607.23442","title":"Do LLM Debates Repeat Arguments Differently Across Languages?","created":"2026-07-26","cited_by_count":0,"area":null},{"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":"2608.22566","title":"From Diagnosis to Redesign: Using Quantitative Ethnography to Improve Multi-Agent LLM Reasoning","created":"2026-08-23","cited_by_count":0,"area":"lr"},{"id":"2608.25152","title":"Belief Cascades Drive Persuasion in LLM Agent Networks","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2609.03619","title":"Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"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":"2609.35279","title":"Measuring Collapse and Correction in Homogeneous-Panel LLM Debate","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.35875","title":"Beyond Symmetric Agents: Cognitive Diversity and Multi-Agent Debate in Small Language Models","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2610.00018","title":"What Do Rationales Communicate? A Message-Intervention Study in Role-Specialized QA","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2610.03095","title":"Peer Influence across Heterogeneous AI Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05615","title":"DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.10468","title":"A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.10608","title":"From Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.10906","title":"Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.20563","title":"Scaling Discovery Requires Forgetting","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}