Evaluating Cooperation in LLM Social Groups through Elected Leadership

2026-04-13

AI Summary

This study addresses the lack of research on how electoral leadership mechanisms foster cooperation and collective decision-making in large language model–based multi-agent systems, particularly in the governance of common-pool resources. To bridge this gap, the work introduces an elected leader with an agenda-driven coordination mechanism into such systems and develops an open-source multi-agent simulation framework. Within a controlled environment, the authors integrate social network analysis and sentiment analysis to investigate how structured leadership influences group-level cooperation. Experimental results demonstrate that incorporating this electoral leadership mechanism increases social welfare by 55.4% and extends group survival duration by 128.6%, thereby providing strong empirical validation of the pivotal role elected leaders play in enhancing cooperative efficiency and overall social welfare.

Technology Category

• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Coordination and Collaboration
• Intelligent Robots: Multi-Robot Systems

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Governing common-pool resources requires agents to develop enduring strategies through cooperation and self-governance to avoid collective failure. While foundation models have shown potential for cooperation in these settings, existing multi-agent research provides little insight into whether structured leadership and election mechanisms can improve collective decision making. The lack of such a critical organizational feature ubiquitous in human society presents a significant shortcoming of the current methods. In this work we aim to directly address whether leadership and elections can support improved social welfare and cooperation through multi-agent simulation with LLMs. We present our open-source framework that simulates leadership through elected personas and candidate-driven agendas and carry out an empirical study of LLMs under controlled governance conditions. Our experiments demonstrate that having elected leadership improves social welfare scores by 55.4% and survival time by 128.6% across a range of high performing LLMs. Through the construction of an agent social graph we compute centrality metrics to assess the social influence of leader personas and also analyze rhetorical and cooperative tendencies revealed through a sentiment analysis on leader utterances. This work lays the foundation for further study of election mechanisms in multi-agent systems toward navigating complex social dilemmas.

Problem

• cooperation
• elected leadership
• multi-agent systems
• common-pool resources
• social dilemmas

Innovation

• elected leadership
• multi-agent simulation
• LLM social groups
• cooperation
• social welfare