指出当前大模型多智能体系统与理论脱节，缺乏真正协同能力。
Large Language Models Miss the Multi-Agent Mark
- 对比理论与实践，揭示现有系统在自主性、社会互动上的缺失
- 识别四类核心差距：社会性、环境设计、协作机制与行为评估
- 呼吁回归经典多智能体理论，避免重复造轮子
近期对大语言模型多智能体系统（MAS LLMs）的兴趣激增，催生了诸多利用多个LLM解决复杂任务的框架。然而，多数研究仅借用‘多智能体’术语，未真正遵循其理论基础。本文指出当前实现与多智能体理论之间存在关键差异，聚焦四个核心领域：智能体的社会性、环境设计、协调与通信协议，以及涌现行为的度量。我们主张，许多MAS LLM缺乏自主性、社会互动和结构化环境等多智能体特征，常依赖过度简化的以LLM为中心的架构。若不反思，该领域可能因重复已有文献解决过的问题而停滞。因此，本文系统分析此问题，提出相关研究机遇，倡导更深入整合成熟多智能体概念与精确术语，以避免误判与错失机会。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。