High Volatility and Action Bias Distinguish LLMs from Humans in Group Coordination

2026-04-02

AI Summary

This study investigates whether large language models (LLMs) can achieve effective group coordination without explicit communication, as humans do, and elucidates the strategic differences between them. Using the Group Binary Search game, the work presents the first systematic comparison of LLMs and human participants in a common-interest, partially observable setting, leveraging human behavioral baselines and mechanism-level metrics—including reactive scaling, switching dynamics, and cross-round learning. The results reveal that LLMs struggle to refine their strategies over successive rounds, exhibiting excessive switching, weak responsiveness to error feedback, and high behavioral volatility. Consequently, LLM groups demonstrate significantly poorer convergence than human groups, highlighting a fundamental limitation of current LLMs in dynamic coordination tasks.

Technology Category

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

Application Category

Economics, Online Markets and Human Computation: Cost models of using LLMs in production systemsUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Humans exhibit remarkable abilities to coordinate in groups. As large language models (LLMs) become more capable, it remains an open question whether they can demonstrate comparable adaptive coordination and whether they use the same strategies as humans. To investigate this, we compare LLM and human performance on a common-interest game with imperfect monitoring: Group Binary Search. In this n-player game, participants need to coordinate their actions to achieve a common objective. Players independently submit numerical values in an effort to collectively sum to a randomly assigned target number. Without direct communication, they rely on group feedback to iteratively adjust their submissions until they reach the target number. Our findings show that, unlike humans who adapt and stabilize their behavior over time, LLMs often fail to improve across games and exhibit excessive switching, which impairs group convergence. Moreover, richer feedback (e.g., numerical error magnitude) benefits humans substantially but has small effects on LLMs. Taken together, by grounding the analysis in human baselines and mechanism-level metrics, including reactivity scaling, switching dynamics, and learning across games, we point to differences in human and LLM groups and provide a behaviorally grounded diagnostic for closing the coordination gap.

Problem

• group coordination
• large language models
• human comparison
• adaptive behavior
• coordination strategies

Innovation

• group coordination
• large language models
• behavioral diagnostics
• switching dynamics
• imperfect monitoring