发表机构
Flowers AI & CogSci Lab; Inria; IT University of Copenhagen; Institute for Advanced Study in Toulouse（Flowers AI与认知科学实验室; 法国国家信息与自动化研究所; 哥本哈根IT大学; 图卢兹高等研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对集体创新任务，提出用LLM引导的进化搜索设计基于状态感知的传输协议，使集体性能较基准提升37%，协议可跨领域与群体迁移，为AI辅助设计协调基础设施提供了路径。
AI 中文摘要
人类集体智能依赖于传输过程：谁与谁分享什么、如何分享以及何时分享。这些过程虽源于个体认知，但也可由刻意的自上而下协议引导。过往研究主要从网络结构视角探讨传输如何塑造集体结果，仅调整谁与谁分享、何时分享，然而网络是与状态无关的，无法根据智能体所知内容或集体状态来调整传输。本文将传输协议形式化为基于智能体和集体状态路由信息与资源的感知状态程序，并使用大语言模型（LLM）引导的进化搜索在集体发现任务中设计有效协议。进化得到的协议使集体性能较文献中的标准基准提升了多达37%。消融实验证实，状态感知是这一优势的驱动因素：在保留网络拓扑结构和时序的同时移除内容依赖性，会消除性能增益。我们还发现，进化得到的协议可跨领域变体和智能体群体迁移。这些结果表明，可在计算机中发现有效且可泛化的传输协议，为设计增强人类集体智能的协调基础设施提供了人工智能辅助的路径。
英文摘要
Human collective intelligence depends on transmission processes: who shares what with whom, how, and when. While these processes emerge from individual cognition, they can also be directed by deliberate top-down protocols. Prior work has studied how transmission shapes collective outcomes primarily through the lens of network structure, varying who shares with whom and when. But networks are state-agnostic: they cannot condition transmission on what agents know or on the state of the collective. Here, we formalize transmission protocols as state-aware programs that route information and resources based on agent and collective states, and we use LLM-guided evolutionary search to design effective protocols in a collective discovery task. Evolved protocols increase collective performance over standard baselines from the literature by up to 37%. Ablations confirm that state-awareness drives this advantage: removing content-dependence while preserving network topology and timing eliminates performance gains. We find that evolved protocols also transfer across domain variations and agent populations. These results demonstrate that effective and generalizable transmission protocols can be discovered in silico, suggesting a path toward AI-assisted design of coordination infrastructure that enhances human collective intelligence.
CommentsCogSci 2026; longer version in prep
