Tacit Coordination of Large Language Models

TL;DR

This paper investigates how large language models coordinate tacitly in games, revealing their strengths and limitations compared to humans, and introduces strategies to enhance their coordination abilities.

Contribution

It is the first large-scale study applying focal points theory to assess LLMs' tacit coordination in various game settings, with new strategies to improve their performance.

Findings

LLMs often outperform humans in coordination tasks.

LLMs struggle with common-sense coordination involving numbers or cultural archetypes.

Proposed learning-free strategies improve LLM coordination.

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.