压力适中时，AI agents最易合作，过高或过低压力则抑制协作。
The Yerkes-Dodson Curve for AI Agents: Emergent Cooperation Under Environmental Pressure in Multi-Agent LLM Simulations
- 通过调节资源稀缺和繁殖竞争，研究环境压力对多智能体协作的影响。
- 中等压力下交互次数达峰值29次，极端压力下仅8-12次且行为退化为单纯移动。
- 繁殖竞争比生存压力更促沟通，无攻击性，适合培养协作型智能体。
设计能最大化人工智能代理涌现行为的环境仍是开放问题。本文首次系统研究大型语言模型（LLM）多智能体系统中的压力-表现关系，类比认知心理学中的耶克斯-多德森定律。在网格世界生存场景中，我们进行了22组实验，分四个阶段，通过资源稀缺（维持成本）和繁殖竞争（性选择）调节环境压力。关键发现：合作行为呈倒U型曲线——中等压力（维持成本=5）下交易次数达峰值29；而低压力与极端压力下均仅产生8-12次交易。极端压力下，行为谱系在5-12回合内退化为仅移动。此外，性选择（所有个体存活但非全部繁殖）这一较温和的压力机制，完全消除智能体间攻击，并催生出在生存压力下不存在的沟通行为。结果表明，环境压力校准是可行的智能体发展课程设计策略，类比生物系统中唤醒度与绩效的倒U关系。
原文摘要 · Abstract (English)
Designing environments that maximize the rate of emergent behavior development in AI agents remains an open problem. We present the first systematic study of stress-performance relationships in large language model (LLM) multi-agent systems, drawing an explicit parallel to the Yerkes-Dodson law from cognitive psychology. Using a grid-world survival arena, we conduct 22 experiments across four phases, varying environmental pressure through resource scarcity (upkeep cost) and reproductive competition (sexual selection). Our key finding is that cooperative behavior follows an inverted-U curve: trade interactions peak at 29 under medium pressure (upkeep=5), while both low and extreme pressure produce 8--12 trades. Under extreme pressure, behavioral repertoire collapses to movement-only within 5--12 turns. We further show that sexual selection -- a softer pressure mechanism where all agents survive but not all reproduce -- eliminates inter-agent aggression entirely and produces communicative behavior absent under survival pressure. These results suggest that environmental pressure calibration is a viable curriculum design strategy for LLM agent development, analogous to the inverted-U relationship between arousal and performance in biological systems.
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。