mlsanityData to 14 Oct 2026

Prompted Identity Degrades Cooperation in Multi-Agent LLM Systems

arXiv 2609.35928 ↗First posted 28 Sep 2026cs.MA cs.AIcited by 0

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

Abstract (arXiv)

Multi-agent LLM systems increasingly mix models from several providers, yet exposing each agent's underlying model identity to its peers significantly impairs cooperation. We show that when agents are aware of each other's model family, the group splits into clusters, where agents prefer interacting with others carrying their same label, although nothing in the task rewards or asks for such a split. We argue that the label itself causes this split, which we define as textitfactionalism. We show and measure this phenomenon in two cooperative games and on a reasoning benchmark, with nine to twenty-five agents drawn from up to five open-weight model families. We further show that when the announced families are shuffled, or replaced by arbitrary labels, the factions still follow this information; when the label is removed, this behavior disappears. In strictly cooperative tasks, labeled groups spend on average 30% more rounds and 55% more tokens to reach a decision, and their success rate drops from 96% to 81%. The effect replicates across tasks, group sizes and model families. Withholding identity labels from the agents is simple and effective mitigation.

Key facts. No citing papers in the map yet (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 24 of its 61 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

24 of 61 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows22 Apr
  2. 2026When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents1 Jan
  3. 2025When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning8 Oct

Other references · 21

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  2. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  4. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  5. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  6. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 686
  7. 2025Why Do Multi-Agent LLM Systems Fail?cited by 604
  8. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 438
  9. 2024Self-Preference Bias in LLM-as-a-Judgecited by 258
  10. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 241
  11. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 178
  12. 2024Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinementcited by 114
9 more
  1. 2023Generative Language Models Exhibit Social Identity Biasescited by 111
  2. 2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 96
  3. 2024Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligencecited by 86
  4. 2025MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learningcited by 86
  5. 2023LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Modelscited by 68
  6. 2024BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systemscited by 26
  7. 2024Autonomous Agents for Collaborative Task under Information Asymmetrycited by 16
  8. 2026Evaluating Cooperation in LLM Social Groups through Elected Leadershipcited by 3
  9. 2026Quantifying Self-Preservation Bias in Large Language Modelscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems
  2. 2026Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation
  3. 2026Multi-agent Scaling Across Disjunctive and Compensatory Tasks
  4. 2026The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
  5. 2026More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration
  6. 2026Don't Make the LLM Read the Graph: Make the Graph Think
  7. 2026Emergent Collusion in Long-Horizon LLM Agent Interaction
  8. 2025Group size effects and collective misalignment in LLM multi-agent systems