{"total":114,"rows":[{"id":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138,"area":"lr"},{"id":"2508.17536","title":"Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?","created":"2025-08-24","cited_by_count":81,"area":"lr"},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2502.08788","title":"Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity","created":"2025-02-12","cited_by_count":44,"area":"lr"},{"id":"2503.22678","title":"Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions","created":"2025-03-28","cited_by_count":40,"area":"agents"},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2312.04854","title":"Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System","created":"2023-12-08","cited_by_count":26,"area":"lr"},{"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":"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":"2504.00762","title":"Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute","created":"2025-04-01","cited_by_count":20,"area":"lr"},{"id":"2505.22960","title":"Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness","created":"2025-05-29","cited_by_count":20,"area":"lr"},{"id":"2412.05449","title":"Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications","created":"2024-12-06","cited_by_count":19,"area":"agents"},{"id":"2602.19843","title":"MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems","created":"2026-02-23","cited_by_count":16,"area":"agents"},{"id":"2509.11656","title":"MALLM: Multi-Agent Large Language Models Framework","created":"2025-09-15","cited_by_count":15,"area":"lr"},{"id":"2507.14928","title":"Byzantine-Robust Decentralized Coordination of LLM Agents","created":"2025-07-20","cited_by_count":14,"area":"agents"},{"id":"2509.20502","title":"MARS: toward more efficient multi-agent collaboration for LLM reasoning","created":"2025-09-24","cited_by_count":13,"area":"lr"},{"id":"2507.08960","title":"How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs","created":"2025-07-11","cited_by_count":12,"area":"lr"},{"id":"2503.12029","title":"Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks","created":"2025-03-15","cited_by_count":11,"area":"agents"},{"id":"2502.08514","title":"Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation","created":"2025-02-12","cited_by_count":10,"area":"agents"},{"id":"2603.05912","title":"DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality","created":"2026-03-06","cited_by_count":10,"area":"agents"},{"id":"2503.23219","title":"Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs","created":"2025-03-29","cited_by_count":9,"area":"lr"},{"id":"2412.15504","title":"Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework","created":"2024-12-20","cited_by_count":8,"area":"agents"},{"id":"2501.07288","title":"LLM-Net: Democratizing LLMs-as-a-Service through Blockchain-based Expert Networks","created":"2025-01-13","cited_by_count":7,"area":null},{"id":"2506.11083","title":"RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates","created":"2025-06-04","cited_by_count":7,"area":"agents"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"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":"2609.21032","title":"Scaling Discovery through Test-Time Communication","created":"2026-09-17","cited_by_count":7,"area":"agents"},{"id":"2408.14575","title":"EVINCE: Optimizing Multi-LLM Dialogues Using Conditional Statistics and Information Theory","created":"2024-08-26","cited_by_count":6,"area":null},{"id":"2510.18032","title":"OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning","created":"2025-10-20","cited_by_count":5,"area":"lr"},{"id":"2511.00181","title":"From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection","created":"2025-10-31","cited_by_count":5,"area":"mllm"},{"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":"2603.27404","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":"2412.13437","title":"Deploying Foundation Model Powered Agent Services: A Survey","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"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":"2603.16244","title":"More Rounds, More Noise: Why Multi-Turn Review Fails to Improve Cross-Context Verification","created":"2026-03-17","cited_by_count":4,"area":null},{"id":"2603.20640","title":"Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention","created":"2026-03-21","cited_by_count":4,"area":"lr"},{"id":"2603.28488","title":"Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification","created":"2026-03-30","cited_by_count":4,"area":"agents"},{"id":"2605.09278","title":"EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium","created":"2026-05-10","cited_by_count":4,"area":"agents"},{"id":"2605.29116","title":"Beyond Consensus: Trace-Level Synthesis in Mixture of Agents","created":"2026-05-27","cited_by_count":4,"area":"agents"},{"id":"2608.03421","title":"When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems","created":"2026-08-04","cited_by_count":4,"area":"agents"},{"id":"2512.06573","title":"The Effect of Belief Boxes and Open-mindedness on Persuasion","created":"2025-12-06","cited_by_count":3,"area":"agents"},{"id":"2601.07232","title":"Yes FLoReNce, I Will Do Better Next Time! Agentic Feedback Reasoning for Humorous Meme Detection","created":"2026-01-12","cited_by_count":3,"area":"agents"},{"id":"2602.02350","title":"Context Learning for Multi-Agent Discussion","created":"2026-02-02","cited_by_count":3,"area":"agents"},{"id":"2602.08013","title":"Small Agent Group is the Future of Digital Health","created":"2026-02-08","cited_by_count":3,"area":"agents"},{"id":"2603.06801","title":"Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy","created":"2026-03-06","cited_by_count":3,"area":"lr"},{"id":"2604.03809","title":"Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus","created":"2026-04-04","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":"2607.26212","title":"Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges","created":"2026-07-28","cited_by_count":3,"area":"agents"},{"id":"2502.12565","title":"Self Iterative Label Refinement via Robust Unlabeled Learning","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2605.10528","title":"Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2606.25191","title":"To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG","created":"2026-06-23","cited_by_count":2,"area":"rag"},{"id":"2607.11250","title":"Multi-Agent LLMs Fail to Explore Each Other","created":"2026-07-13","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":"2404.13071","title":"Modeling Emotions and Ethics with Large Language Models","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2501.14917","title":"Self-reflecting Large Language Models: A Hegelian Dialectical Approach","created":"2025-01-24","cited_by_count":1,"area":null},{"id":"2504.09781","title":"Reasoning Court: Combining Reasoning, Action, and Judgment for Multi-Hop Reasoning","created":"2025-04-14","cited_by_count":1,"area":"lr"},{"id":"2510.06240","title":"Knowledge Graph-Guided Multi-Agent Distillation for Reliable Industrial Question Answering with Datasets","created":"2025-10-03","cited_by_count":1,"area":"agents"},{"id":"2512.23717","title":"HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debate","created":"2025-12-09","cited_by_count":1,"area":"agents"},{"id":"2601.22297","title":"Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"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":"2604.02923","title":"Council Mode: A Heterogeneous Multi-Agent Consensus Framework for Reducing LLM Hallucination and Bias","created":"2026-04-03","cited_by_count":1,"area":"agents"},{"id":"2605.20548","title":"What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2605.22949","title":"MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination","created":"2026-05-21","cited_by_count":1,"area":"agents"},{"id":"2606.00804","title":"Dynamic Coordination Strategy Selection for Enterprise Multi-Agent Systems","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2607.14713","title":"Does Multi-Agent Debate Improve AI Feedback on Research Papers?","created":"2026-07-16","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":"2609.02264","title":"Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems","created":"2026-09-02","cited_by_count":1,"area":"agents"},{"id":"2609.04871","title":"AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2609.38345","title":"OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2502.18653","title":"Enhancing Text Classification with a Novel Multi-Agent Collaboration Framework Leveraging BERT","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2603.27150","title":"MediHive: A Decentralized Agent Collective for Medical Reasoning","created":"2026-03-28","cited_by_count":0,"area":"lr"},{"id":"2603.28813","title":"The impact of multi-agent debate protocols on debate quality: a controlled case study","created":"2026-03-28","cited_by_count":0,"area":"agents"},{"id":"2604.10389","title":"BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection","created":"2026-04-12","cited_by_count":0,"area":"rag"},{"id":"2604.14969","title":"Discovering Novel LLM Experts via Task-Capability Coevolution","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.22820","title":"Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Long-Horizon Workflows","created":"2026-04-17","cited_by_count":0,"area":"agents"},{"id":"2605.13839","title":"Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights","created":"2026-05-13","cited_by_count":0,"area":"agents"},{"id":"2605.22208","title":"EvoIR-Agent: Self-Evolving Image Restoration Agentic System via Experience-Driven Learning","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2605.25929","title":"Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?","created":"2026-05-25","cited_by_count":0,"area":"agents"},{"id":"2605.27621","title":"Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2605.27864","title":"FundaPod: A Multi-Persona Agent Pod Architecture with Knowledge Graph Memory for AI-Assisted Fundamental Investment Research","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2605.30391","title":"Social Reasoning in Machines: Investigating Collective Truth-Seeking Dynamics in Large Language Model Debate","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"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":"2607.15095","title":"Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents","created":"2026-07-16","cited_by_count":0,"area":"agents"},{"id":"2607.21912","title":"Reliability-Contagion Feasibility in LLM Multi-Agent Networks","created":"2026-07-24","cited_by_count":0,"area":"agents"},{"id":"2608.00685","title":"When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Cost, and Task Difficulty","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.08605","title":"ForestBench: A Unified Graph Framework for Evaluating Multi-Agent Collaboration","created":"2026-08-09","cited_by_count":0,"area":"agents"},{"id":"2608.16213","title":"Process-Constituted Intelligence: A Shared Criterion for Humans and Machines","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.18167","title":"Adversarial Review: Structured Disagreement for Grounded Agentic Code Review","created":"2026-08-16","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":"2609.01168","title":"Jailbreaking Text-to-Image Models Through Cracks: Navigating Heterogeneous Safety Filters via Multi-Agent Debate","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.07573","title":"From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interaction","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":"2609.11109","title":"How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative Coding","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.13261","title":"From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration","created":"2026-09-06","cited_by_count":0,"area":"agents"},{"id":"2609.26145","title":"Unanimity Without Persuasion: A Single Round of Debate Erases the Disagreement That Verification Needs","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.27150","title":"Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.27822","title":"What Confidence Routing Is Actually Doing: Auditing Routing, Calibration, and Commitment in Multi-Agent Deliberation","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.31422","title":"Towards Mitigating Fabricated Consensus: The Active Provenance Gate for Multi-Agent Debate Synthesis","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.34444","title":"Social Circuits behind Multi-agent Echo Chambers","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.35551","title":"BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":"100"}