Tacit Coordination of Large Language Models

2026-01-28

AI Summary

This study addresses the challenge of how large language models (LLMs) effectively identify and select Schelling focal points to achieve efficient coordination in multi-equilibrium tacit coordination games. Within the framework of focal point theory, the work presents the first large-scale evaluation of various open-source LLMs—including Llama, Qwen, and GPT-oss—on both cooperative and competitive coordination tasks. Integrating psychological experimental paradigms with game-theoretic methods, the authors propose training-free, zero-shot prompting and reasoning strategies. Results show that LLMs outperform human participants in most tasks, yet exhibit notable limitations in scenarios requiring numerical common sense or sensitivity to cultural nuances. The proposed strategies significantly enhance the models’ coordination performance, demonstrating both effectiveness and generalizability across diverse settings.

Technology Category

• Game Theory and Economic Paradigms: Coordination and Collaboration
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

In tacit coordination games with multiple outcomes, purely rational solution concepts, such as Nash equilibria, provide no guidance for which equilibrium to choose. Shelling's theory explains how, in these settings, humans coordinate by relying on focal points: solutions or outcomes that naturally arise because they stand out in some way as salient or prominent to all players. This work studies Large Language Models (LLMs) as players in tacit coordination games, and addresses how, when, and why focal points emerge. We compare and quantify the coordination capabilities of LLMs in cooperative and competitive games for which human experiments are available. We also introduce several learning-free strategies to improve the coordination of LLMs, with themselves and with humans. On a selection of heterogeneous open-source models, including Llama, Qwen, and GPT-oss, we discover that LLMs have a remarkable capability to coordinate and often outperform humans, yet fail on common-sense coordination that involves numbers or nuanced cultural archetypes. This paper constitutes the first large-scale assessment of LLMs'tacit coordination within the theoretical and psychological framework of focal points.

Problem

• tacit coordination
• focal points
• large language models
• Nash equilibria
• human-AI coordination

Innovation

• tacit coordination
• focal points
• large language models
• learning-free strategies
• human-AI coordination