Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches

2025-10-07

AI Summary

This study investigates effective coordination mechanisms for cooperation in multi-agent large language model (LLM) systems, focusing on coordination problems and social dilemmas. We comparatively evaluate two paradigms—direct communication and curriculum learning—across two canonical game-theoretic settings: the 4-player Stag Hunt and the iterated public goods game with punishment. Results show that introducing a minimal “cheap talk” channel—requiring only single-character utterances—increases cooperation rates from 0% to 48.3%, demonstrating the robustness and efficiency of lightweight communication as a coordination mechanism. In contrast, structured curriculum learning leads to a 27.4% average payoff reduction among agents and induces learned pessimism. The work innovatively reveals the low-threshold, high-return nature of communication for multi-agent cooperation, while cautioning against unintended negative effects of curriculum design. These findings provide scalable, interpretable intervention strategies for enhancing collaborative behavior in LLM-based multi-agent systems.

Technology Category

• Multiagent Systems: Agent Communication
• Machine Learning: Large Multimodal Models (LMMs)
• Game Theory and Economic Paradigms: Coordination and Collaboration

Application Category

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

Abstract

Eliciting cooperation in multi-agent LLM systems is critical for AI alignment. We investigate two approaches: direct communication and curriculum learning. In a 4-player Stag Hunt, a one-word "cheap talk" channel increases cooperation from 0% to 48.3%, demonstrating communication as a robust coordination mechanism. In contrast, we find that curriculum learning is highly sensitive to design choices: our pedagogical curriculum through progressively complex games reduced agent payoffs by 27.4% in an Iterated Public Goods Game with Punishment. Qualitative analysis reveals that curricula emphasizing defection-equilibrium games can induce "learned pessimism" in agents. These findings suggest that for coordination problems, simple communication protocols may be more reliable than experience-based training, and that curriculum design for social dilemmas requires careful attention to the strategic lessons embedded in game sequences.

Problem

• Investigating communication versus curriculum learning for multi-agent cooperation
• Evaluating cheap talk's impact on coordination in Stag Hunt games
• Analyzing curriculum design sensitivity in social dilemma training paradigms

Innovation

• Direct communication enables cooperation in multi-agent systems
• Cheap talk channel significantly increases coordination rates
• Communication protocols outperform complex curriculum learning approaches