普林斯顿论文：多开发者专用智能体组合在 GAIA 达 70%
普林斯顿：多开发者专用智能体组合GAIA达70%
普林斯顿一篇新论文通过模拟固定预算下由 LLM 智能体构建智能体的开发者群体，发现把多个开发者各自构建的专用智能体组合起来，在 GAIA 上准确率达 70%。在相同总开发预算下，单独得分最高仅 35% 的专用智能体组合后达到 70%，比通用智能体中位数高 12 个百分点；但在仅需网页搜索的 SealQA 上，组合系统成本更高且表现更差。
Rohan Paul· @rohanpaul_ai · X·2026-10-20 15:53· 44 分钟前AI 评分50
AI 导读
普林斯顿论文发现，将多个开发者各自构建的专用智能体组合起来，可超越任何单一开发者的通用智能体，GAIA准确率达70%。在相同总开发预算下，单独得分最高仅35%的专用智能体组合后达到70%，比通用智能体中位数高12个百分点；但在仅需网页搜索的SealQA上，组合系统成本更高且表现更差。作者认为智能体应填补共享系统的空白：单独得分19%的智能体可将组合系统从40%提升至53%。
正文 · 原文
New Princeton paper finds that combining specialized agents from many developers can beat any single developer's general agent, with GAIA accuracy reaching 70%.
Today most agentic systems are built and controlled by 1 developer, so each team rebuilds the same basic skills. The authors argue this limits scale.
They simulated populations of developers with LLM agents that build agents under a fixed budget, then compared lone systems with a multi-developer system. The multi-developer system splits each task and routes the parts to different developers' agents.
On GAIA with the same total development budget, specialists that each scored at most 35% alone reached 70% together. That is 12 points above the median general agent, while on web-search-only SealQA the combined system did worse at higher cost.
Build agents to fill gaps in shared systems, since an agent scoring 19% alone lifted a combined system from 40% to 53%.
来源：Rohan Paul · x.com
来源：RadarAI · aihot.news