mlsanityData to 14 Oct 2026

The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems

arXiv 2509.26126 ↗First posted 30 Sep 2025cs.CLcited by 1

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

LLM-based multi-agent systems demonstrate great potential for tackling complex problems, but how competition shapes their behavior remains underexplored. This paper investigates the over-competition in multi-agent debate, where agents under extreme pressure exhibit unreliable, harmful behaviors that undermine both collaboration and task performance. To study this phenomenon, we propose HATE, the Hunger Game Debate, a novel experimental framework that simulates debates under a zero-sum competition arena. Our experiments, conducted across a range of LLMs and tasks, reveal that competitive pressure significantly stimulates over-competition behaviors and degrades task performance, causing discussions to derail. We further explore the impact of environmental feedback by adding variants of judges, indicating that objective, task-focused feedback effectively mitigates the over-competition behaviors. We also probe the post-hoc kindness of LLMs and form a leaderboard to characterize top LLMs, providing insights for understanding and governing the emergent social dynamics of AI community.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 49 of its 65 references that are in the map. First posted on arXiv 30 Sep 2025.

Builds on

49 of 65 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions24 Aug
  2. 2024Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View23 May
  3. 2023War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars28 Nov
  4. 2023LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay23 Oct
  5. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate30 May
  6. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 43

  1. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  2. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  4. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  5. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,184
  6. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  7. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  8. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  9. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
  10. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  11. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 266
  12. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaborationcited by 251
31 more
  1. 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 241
  2. 2023Building Cooperative Embodied Agents Modularly with Large Language Modelscited by 237
  3. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 233
  4. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 206
  5. 2025BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agentcited by 200
  6. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 178
  7. 2024Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fastcited by 153
  8. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Modelscited by 135
  9. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 134
  10. 2022Evaluating and Inducing Personality in Pre-trained Language Modelscited by 123
  11. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithmscited by 113
  12. 2024Symbolic Learning Enables Self-Evolving Agentscited by 106
  13. 2025MasRouter: Learning to Route LLMs for Multi-Agent Systemscited by 88
  14. 2024Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communitiescited by 86
  15. 2024Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voterscited by 71
  16. 2024AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitionscited by 70
  17. 2024Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent Systemcited by 68
  18. 2024ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agentscited by 35
  19. 2025Robotouille: An Asynchronous Planning Benchmark for LLM Agentscited by 32
  20. 2024Multi-Agent Collaboration via Cross-Team Orchestrationcited by 30
  21. 2024BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systemscited by 26
  22. 2025Large Language Models Miss the Multi-Agent Markcited by 26
  23. 2024Measuring and Improving Persuasiveness of Large Language Modelscited by 20
  24. 2025GA-S3: Comprehensive Social Network Simulation with Group Agentscited by 19
  25. 2024Can LLMs make trade-offs involving stipulated pain and pleasure states?cited by 16
  26. 2025Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failurecited by 13
  27. 2023The Good, The Bad, and Why: Unveiling Emotions in Generative AIcited by 10
  28. 2025Do Large Language Model Agents Exhibit a Survival Instinct? An Empirical Study in a Sugarscape-Style Simulationcited by 9
  29. 2024EVINCE: Optimizing Multi-LLM Dialogues Using Conditional Statistics and Information Theorycited by 6
  30. 2025Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysiscited by 6
  31. 2025The AI in the Mirror: LLM Self-Recognition in an Iterated Public Goods Gamecited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Reliable agent engineering should integrate machine-compatible organizational principlescited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026Emergence of Biased Consensus in Multi-Agent LLM Debates
  2. 2025Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate
  3. 2025Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate
  4. 2025The Social Laboratory: A Psychometric Framework for Multi-Agent LLM Evaluation
  5. 2024I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy
  6. 2025When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?
  7. 2026The Yerkes-Dodson Curve for AI Agents: Emergent Cooperation Under Environmental Pressure in Multi-Agent LLM Simulations
  8. 2026Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent Game Tournaments