Large Language Models Miss the Multi-Agent Mark

TL;DR

This paper critically examines the gap between multi-agent system theory and current large language model implementations, emphasizing the need for better integration of MAS principles to advance the field.

Contribution

It highlights key discrepancies between MAS theory and LLM-based MAS implementations and advocates for incorporating established MAS concepts and terminology.

Findings

Current MAS LLMs lack true multi-agent characteristics

Many implementations rely on oversimplified LLM-centric architectures

Revisiting existing MAS problems may hinder progress

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.