单智能体能力提升无法自动带来多智能体协作，需专门设计基础模型。
Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence
- 提出多智能体核心能力：理解、规划、通信与适应。
- 41个大模型实验证明，单智能体规模增长不等于多智能体智能提升。
- 面向未来多智能体系统，需构建专用数据集与评估体系。
基础模型（FMs）正逐渐成为智能体的‘大脑’。尽管近期研究已开始赋予其原生单智能体能力（如界面交互或工具集成），我们指出，下一前沿是让基础模型具备原生多智能体智能。本文识别出多智能体场景下基础模型的四项核心能力：理解、规划、高效通信与适应性。与假设其能自发涌现不同，我们在41个大型语言模型和7个具有挑战性的基准上提供了充分的实证证据，表明仅靠提升单智能体性能无法自动获得稳健的多智能体智能。为填补这一差距，本文提出了关键研究方向，涵盖数据集构建、评估方法、训练范式与安全考量，以推动具备原生多智能体智能的基础模型发展。
原文摘要 · Abstract (English)
Foundation models (FMs) are increasingly assuming the role of the ''brain'' of AI agents. While recent efforts have begun to equip FMs with native single-agent abilities -- such as GUI interaction or integrated tool use -- we argue that the next frontier is endowing FMs with native multi-agent intelligence. We identify four core capabilities of FMs in multi-agent contexts: understanding, planning, efficient communication, and adaptation. Contrary to assumptions about the spontaneous emergence of such abilities, we provide extensive empirical evidence, across 41 large language models and 7 challenging benchmarks, showing that scaling single-agent performance alone does not automatically yield robust multi-agent intelligence. To address this gap, we outline key research directions -- spanning dataset construction, evaluation, training paradigms, and safety considerations -- for building FMs with native multi-agent intelligence.
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。