mlsanityData to 14 Oct 2026

Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest

arXiv 2604.25088 ↗First posted 28 Apr 2026cs.AI cs.CLcited by 0

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

Abstract (arXiv)

Language Model (LM)-based agents remain largely untested in mixed-motive settings where agents must leverage short-term cooperation for long-term competitive goals (e.g., multi-party politics). We introduce Cooperate to Compete (C2C), a multi-agent environment where players can engage in private negotiations while competing to be the first to achieve their secret objective. Players have asymmetric objectives and negotiations are non-binding, allowing alliances to form and break as players' short-term interests align and diverge. We run AI only games and conduct a user study pitting human players against AI opponents. We identify significant differences between human and AI negotiation behaviors, finding that humans favor lower-complexity deals and are significantly less reliable partners compared to LM-based agents. We also find that humans are more aggressive negotiators, accepting deals without a counteroffer only 56.3% of the time compared to 67.6% for LM-based agents. Through targeted prompting inspired by these findings, we modify agents' negotiation behavior and improve win rates from 22.2% to 32.7%. We run over 1,100 games with over 16,000 private conversations totaling 15.2 million tokens and over 150,000 player actions. Our results establish C2C as a testbed for studying and building LM-based agents that can navigate the sophisticated coordination required for real-world deployments. The game, code, and dataset may be found at https://negotiationgame.io/c2c.

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 18 of its 39 references that are in the map. First posted on arXiv 28 Apr 2026.

Builds on

18 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models6 Mar

Other references · 17

  1. 2022Using cognitive psychology to understand GPT-3cited by 398
  2. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 367
  3. 2023Playing repeated games with Large Language Modelscited by 217
  4. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 178
  5. 2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 96
  6. 2023MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaborationcited by 57
  7. 2024BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systemscited by 26
  8. 2024(Ir)rationality and Cognitive Biases in Large Language Modelscited by 23
  9. 2024COMMA: A Communicative Multimodal Multi-Agent Benchmarkcited by 14
  10. 2024FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learningcited by 13
  11. 2025The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperationcited by 13
  12. 2025Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordiacited by 12
5 more
  1. 2025Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategiescited by 10
  2. 2024More Victories, Less Cooperation: Assessing Cicero's Diplomacy Playcited by 9
  3. 2025Bounded Rationality for LLMs: Satisficing Alignment at Inference-Timecited by 9
  4. 2025Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approachescited by 4
  5. 2026Communication Enhances LLMs' Stability in Strategic Thinkingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Payoff scaling shapes cooperation in LLM agents across languages
  2. 2025Strategic Tradeoffs Between Humans and AI in Multi-Agent Bargaining
  3. 2026Competition and Cooperation of LLM Agents in Games
  4. 2025Collaboration and Conflict between Humans and Language Models through the Lens of Game Theory
  5. 2026More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration
  6. 2025When Trust Collides: Decoding Human-LLM Cooperation Dynamics through the Prisoner's Dilemma
  7. 2024Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
  8. 2024Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents