Discovering Adaptive Transmission Programs for Collective Innovation

2026-08-25

AI Summary

研究通过使用基于LLM的进化搜索设计状态感知传输协议，以提高集体创新任务中的表现，相比传统方法提升高达37%。

Abstract

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.

Problem

• transmission protocols
• collective intelligence
• state-aware
• network structure
• information routing

Innovation

• state-aware transmission protocols
• LLM-guided evolutionary search
• collective discovery task
• performance improvement