Generative Emergent Communication: Large Language Model is a Collective World Model

2024-12-31

AI Summary

This work addresses the origins of symbolic communication, language evolution, and multi-agent collaborative learning—particularly within large language model (LLM) interactions—where theoretical gaps persist between individual cognitive development and socio-linguistic emergence. Method: We propose Generative Emergent Communication (EmCom), a unified framework grounded in Collective Predictive Coding (CPC) that jointly models language emergence, world representation, and LLM internal mechanisms. EmCom formalizes LLMs as “collective world models” integrating multi-agent experiential priors. Leveraging the “control-as-inference” paradigm, we develop a generative theory of communication, integrating CPC, Bayesian inference, multi-agent reinforcement learning, and formal symbolic system modeling. Contribution/Results: EmCom provides a unified account of language emergence, uncovers deep mechanisms underlying LLM generalization and alignment, and enables principled design of interpretable, robust human–AI and multi-agent collaborative systems.

Technology Category

• Natural Language Processing: (Large) Language Models
• Multiagent Systems: Agent Communication
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• 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
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

This study proposes a unifying theoretical framework called generative emergent communication (generative EmCom) that bridges emergent communication, world models, and large language models (LLMs) through the lens of collective predictive coding (CPC). The proposed framework formalizes the emergence of language and symbol systems through decentralized Bayesian inference across multiple agents, extending beyond conventional discriminative model-based approaches to emergent communication. This study makes the following two key contributions: First, we propose generative EmCom as a novel framework for understanding emergent communication, demonstrating how communication emergence in multi-agent reinforcement learning (MARL) can be derived from control as inference while clarifying its relationship to conventional discriminative approaches. Second, we propose a mathematical formulation showing the interpretation of LLMs as collective world models that integrate multiple agents' experiences through CPC. The framework provides a unified theoretical foundation for understanding how shared symbol systems emerge through collective predictive coding processes, bridging individual cognitive development and societal language evolution. Through mathematical formulations and discussion on prior works, we demonstrate how this framework explains fundamental aspects of language emergence and offers practical insights for understanding LLMs and developing sophisticated AI systems for improving human-AI interaction and multi-agent systems.

Problem

• Symbolic Communication
• Language Development
• Collaborative Learning

Innovation

• Generative EmCom
• Multi-agent Collaborative Learning
• Symbolic Communication Origins