用AI设计会根据状态自适应调整的信息传递规则，提升群体创新效率。
Discovering Adaptive Transmission Programs for Collective Innovation
- 将信息传递规则建模为感知个体与集体状态的程序，实现动态调度。
- 在群体发现任务中，性能相比基线最高提升37%。
- 规则具有跨领域和人群的泛化能力，适合用于AI辅助协作系统设计。
人类集体智能依赖于信息传递过程：谁在何时向谁分享什么内容。尽管这些过程源于个体认知，也可通过自上而下的协议进行引导。以往研究主要从网络结构角度分析传递如何影响集体结果，但传统网络是状态无关的，无法依据个体知识或集体状态进行调节。本文将传递协议形式化为状态感知的程序，根据个体与集体状态动态路由信息与资源，并利用大模型引导的演化搜索，在集体发现任务中设计出高效协议。所获得的协议相比文献中的标准基线，集体表现提升高达37%。消融实验表明，状态感知是性能优势的关键：若移除内容依赖性但保留网络拓扑与时间安排，则性能增益消失。此外，进化出的协议在不同任务域与不同代理群体间均表现出良好迁移性。结果表明，有效的、可泛化的传递协议可通过计算方式发现，为借助AI设计增强人类集体智能的协同基础设施提供了新路径。
原文摘要 · Abstract (English)
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.
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。