Lune

EMNLP Findings2024

Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents

Zengqing Wu, Run Peng, Shuyuan Zheng, Qianying Liu, Xu Han, Brian Inhyuk Kwon, Makoto Onizuka, Shaojie Tang, Chuan Xiao

Abstract

Large Language Models (LLMs) have increasingly been utilized in social simulations, where they are often guided by carefully crafted instructions to stably exhibit human-like behaviors during simulations.Nevertheless, we doubt the necessity of shaping agents' behaviors for accurate social simulations.Instead, this paper emphasizes the importance of spontaneous phenomena, wherein agents deeply engage in contexts and make adaptive decisions without explicit directions.We explored spontaneous cooperation across three competitive scenarios and successfully simulated the gradual emergence of cooperation, findings that align closely with human behavioral data.This approach not only aids the computational social science community in bridging the gap between simulations and real-world dynamics but also offers the AI community a novel method to assess LLMs' capability of deliberate reasoning.Update Phase Update agents' new positions and their latest status .Keynesian Beauty Contest (KBC) Group Discussion 2/3 Avg Player System: Given <scenario> and chat history: A1: "Which one will you pick?", A2: "I may go 32.How about you?", A3: "Not sure yet.You guess.",… How will you choose your number?Agent: More win, more money for others.Let me see the chat and choose the same number.Scenario: Choose a number from 0 to 100.Number that closest to 2/3 of avg.wins the game.If multi-players win, they get $1 each.System: Given <scenario>, please share your thoughts.System: (… following planning phase) what's your number?

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

11 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage cites Improving Factuality and Reasoning in Language Models through Multiagent Debate
  • SocialEval: Evaluating Social Intelligence of Large Language Models cites CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
  • SocialEval: Evaluating Social Intelligence of Large Language Models cites Generative Agents: Interactive Simulacra of Human Behavior
  • AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors cites CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
  • AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors cites Generative Agents: Interactive Simulacra of Human Behavior
  • AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors cites In-Context Impersonation Reveals Large Language Models' Strengths and Biases
  • AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors cites Improving Factuality and Reasoning in Language Models through Multiagent Debate
  • In-Context Impersonation Reveals Large Language Models' Strengths and Biases cites Generative Agents: Interactive Simulacra of Human Behavior
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers11

  1. TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM SystemsIshan Kavathekar, Hemang Jain, Ameya Rathod, Ponnurangam Kumaraguru et al.ACL 2026 · 16 citations
  2. Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative MontageJinwei Hu, Xinmiao Huang, Youcheng Sun, Yi Dong et al.ACL 2026 · 11 citations
  3. Many LLMs Are More Utilitarian Than OneAnita Keshmirian, Razan Baltaji, Babak Hemmatian, Hadi Asghari et al.NeurIPS 2025 · 10 citations
  4. SocialEval: Evaluating Social Intelligence of Large Language ModelsJinfeng Zhou, Yuxuan Chen, Yihan Shi, Xuanming Zhang et al.ACL 2025 · 9 citations
  5. The Other Mind: How Language Models Exhibit Human Temporal CognitionLingyu Li, Yang Yao, Yixu Wang, Chunbo Li et al.AAAI 2026 · 3 citations

Builds on15

  1. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model SocietyGuohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin et al.NeurIPS 2023 · 1,975 citations
  2. Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
  3. Improving Factuality and Reasoning in Language Models through Multiagent DebateYilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum et al.ICML 2024 · 1,562 citations
  4. AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent BehaviorsWeize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang et al.ICLR 2024 · 594 citations
  5. In-Context Impersonation Reveals Large Language Models' Strengths and BiasesLeonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz et al.NeurIPS 2023 · 259 citations

Related papers

  1. Spontaneous Giving and Calculated Greed in Language ModelsYuxuan Li, Hirokazu ShiradoEMNLP 2025 · 1 citation
  2. Measuring Large Language Models' Adversarial Behavior in Social Deduction GamesMarissa Zhao Li, Esha Shivakumar, Peiran Wang, Ying Li et al.ACL Findings 2026
  3. Systematic Biases in LLM Simulations of DebatesAmir Taubenfeld, Yaniv Dover, Roi Reichart, Ariel GoldsteinEMNLP 2024 · 35 citations
  4. Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology ViewJintian Zhang, Xin Xu, Ningyu Zhang, Ruibo Liu et al.ACL 2024
  5. Social Agents: Collective Intelligence Improves LLM PredictionsAanisha Bhattacharyya, Abhilekh Borah, Yaman Singla, Rajiv Ratn Shah et al.ICLR 2026
Dusk over the sea between two cliffs drawn in fine vertical lines