The Power of Stories: Narrative Priming Shapes How LLM Agents Collaborate and Compete
This addresses how to design multi-agent systems for better cooperation, but it is incremental as it applies known priming concepts to LLMs.
The study tackled the problem of whether narrative priming can influence LLM agents' collaboration in a public goods game, finding that common stories improve cooperation while different stories reduce it, with specific effects on negotiation strategies and success rates.
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.