Large Language Models Miss the Multi-Agent Mark

2025-05-27

AI Summary

Contemporary large language model–driven multi-agent systems (MAS LLMs) significantly deviate from classical multi-agent theory, exhibiting deficiencies in agent autonomy, social interaction, environmental embedding, coordination mechanisms, and evaluation of emergent behavior. This paper systematically identifies— for the first time—four fundamental theoretical gaps in MAS LLMs: autonomy, sociability, environmental situatedness, and coordination paradigms. Using theoretical multi-agent analysis, conceptual mapping, and cross-paradigmatic critical comparison—without reliance on specific algorithmic implementations—we diagnose these misalignments. Our core contributions are: (i) formal criteria for terminological rigor in MAS LLM research, and (ii) an architectural reorientation pathway that shifts MAS LLMs away from LLM-centric design toward a genuine multi-agent paradigm grounded in autonomy, sociality, and environmental embedding. This work establishes a foundational theoretical anchor and a principled development framework for the field. (149 words)

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures

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
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Recent interest in Multi-Agent Systems of Large Language Models (MAS LLMs) has led to an increase in frameworks leveraging multiple LLMs to tackle complex tasks. However, much of this literature appropriates the terminology of MAS without engaging with its foundational principles. In this position paper, we highlight critical discrepancies between MAS theory and current MAS LLMs implementations, focusing on four key areas: the social aspect of agency, environment design, coordination and communication protocols, and measuring emergent behaviours. Our position is that many MAS LLMs lack multi-agent characteristics such as autonomy, social interaction, and structured environments, and often rely on oversimplified, LLM-centric architectures. The field may slow down and lose traction by revisiting problems the MAS literature has already addressed. Therefore, we systematically analyse this issue and outline associated research opportunities; we advocate for better integrating established MAS concepts and more precise terminology to avoid mischaracterisation and missed opportunities.

Problem

• MAS LLMs lack multi-agent autonomy and social interaction
• Current MAS LLMs oversimplify environment and coordination design
• MAS LLMs misapply terminology without foundational MAS principles

Innovation

• Integrates established Multi-Agent System principles
• Highlights discrepancies in MAS LLM implementations
• Advocates precise terminology and social interaction