mlsanityData to 14 Oct 2026

The Power of Stories: Narrative Priming Shapes How LLM Agents Collaborate and Compete

arXiv 2505.03961 ↗First posted 6 May 2025cs.AI cs.CL cs.MAcited by 2

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

Abstract (arXiv)

According to Yuval Noah Harari, large-scale human cooperation is driven by shared narratives that encode common beliefs and values. This study explores whether such narratives can similarly nudge LLM agents toward collaboration. We use a finitely repeated public goods game in which LLM agents choose either cooperative or egoistic spending strategies. We prime agents with stories highlighting teamwork to different degrees and test how this influences negotiation outcomes. Our experiments explore four questions:(1) How do narratives influence negotiation behavior? (2) What differs when agents share the same story versus different ones? (3) What happens when the agent numbers grow? (4) Are agents resilient against self-serving negotiators? We find that story-based priming significantly affects negotiation strategies and success rates. Common stories improve collaboration, benefiting each agent. By contrast, priming agents with different stories reverses this effect, and those agents primed toward self-interest prevail. We hypothesize that these results carry implications for multi-agent system design and AI alignment.

Key facts. Cited by 2 papers 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 11 of its 35 references that are in the map. First posted on arXiv 6 May 2025.

Builds on

11 of 35 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis8 Feb
  2. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 9

  1. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
  2. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  3. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Modelscited by 135
  4. 2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 96
  5. 2024Are LLMs Effective Negotiators? Systematic Evaluation of the Multifaceted Capabilities of LLMs in Negotiation Dialoguescited by 29
  6. 2024Steering Language Models with Game-Theoretic Solverscited by 28
  7. 2024Do Language Models Exhibit Human-like Structural Priming Effects?cited by 21
  8. 2015Negotiation Gamescited by 1
  9. 2024Reporting and Analysing the Environmental Impact of Language Models on the Example of Commonsense Question Answering with External Knowledgecited by 1

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societiescited by 14
  2. 2025LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancementscited by 9

Similar, not cited

Close in wording, no citation either way

  1. 2026Social Catalysts, Not Moral Agents: The Illusion of Alignment in LLM Societies
  2. 2026The Story Shapes the Agent: Narrative Priors in LLM Behavior
  3. 2026Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest
  4. 2025When Trust Collides: Decoding Human-LLM Cooperation Dynamics through the Prisoner's Dilemma
  5. 2025Strategic Tradeoffs Between Humans and AI in Multi-Agent Bargaining
  6. 2025Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes
  7. 2026Moral Hazard in Multi-Agent Language Models
  8. 2026Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation