让大模型智能体自发协作，比人工设计结构更高效。
Drop the Hierarchy and Roles: How Self-Organizing LLM Agents Outperform Designed Structures
- 用最小结构约束，让智能体自发形成角色分工。
- 自主协作方案比集中控制提升14%表现，差异显著。
- 能力强的模型更易自组织，适合大规模部署。
我们开展了涵盖8个模型、4至256个智能体、8种协调协议（从外部强加层级到自发自组织）的25,000任务计算实验。结果发现，当前大模型智能体在仅需固定顺序的极简结构下，即可自发产生专业化角色、主动回避非专长任务并形成浅层层级，无需预设角色或外部设计。一种支持自主性的混合协议（顺序式）比中心化协调提升14%（p<0.001），协议间质量差距达44%（Cohen's d=1.86，p<0.0001）。智能体自主性随模型能力提升而增强：强模型能有效自组织，弱模型仍需刚性结构——表明随着基础模型进步，自主协调空间将扩大。系统扩展至256智能体时性能无下降（p=0.61），8个智能体即生成5,006种独特角色。结果在闭源与开源模型中均复现，开源模型以24倍成本优势达成闭源95%的性能。
原文摘要 · Abstract (English)
How much autonomy can multi-agent LLM systems sustain -- and what enables it? We present a 25,000-task computational experiment spanning 8 models, 4--256 agents, and 8 coordination protocols ranging from externally imposed hierarchy to emergent self-organization. We observe that autonomous behavior already emerges in current LLM agents: given minimal structural scaffolding (fixed ordering), agents spontaneously invent specialized roles, voluntarily abstain from tasks outside their competence, and form shallow hierarchies -- without any pre-assigned roles or external design. A hybrid protocol (Sequential) that enables this autonomy outperforms centralized coordination by 14% (p<0.001), with a 44% quality spread between protocols (Cohen's d=1.86, p<0.0001). The degree of emergent autonomy scales with model capability: strong models self-organize effectively, while models below a capability threshold still benefit from rigid structure -- suggesting that as foundation models improve, the scope for autonomous coordination will expand. The system scales sub-linearly to 256 agents without quality degradation (p=0.61), producing 5,006 unique roles from just 8 agents. Results replicate across closed- and open-source models, with open-source achieving 95% of closed-source quality at 24x lower cost. The practical implication: give agents a mission, a protocol, and a capable model -- not a pre-assigned role.
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。