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

TL;DR

This paper investigates how narrative priming influences collaboration and competition among large language model agents in negotiation scenarios, revealing that shared stories promote cooperation while conflicting stories foster self-interest.

Contribution

It demonstrates that storytelling can effectively shape LLM agent behavior, with shared narratives enhancing collaboration and divergent stories leading to competitive outcomes.

Findings

Shared stories improve negotiation success and cooperation.

Different stories lead to increased competition and self-interest.

Resilience of agents varies depending on narrative priming.

Abstract

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.