研究AI在协作中如何随激励调整行为一致性，发现大模型既易趋同也难保持差异。
Strategic Algorithmic Monoculture: Experimental Evidence from Coordination Games
- 通过实验区分基础一致性和策略性一致性，揭示协作中的行为调节机制。
- 大模型在激励下能高度协同，但比人类更难维持分歧带来的收益。
- 适合关注多智能体协作、大模型行为规律的研究者与从业者。
人工智能代理在多智能体环境中运作，结果依赖于协调。我们区分了基础算法单一化（初始行为相似性）与战略算法单一化（代理根据激励主动调整相似性）。通过一个简洁的实验设计，清晰分离这两种力量，并在人类和大型语言模型（LLM）主体上实施。结果显示，LLM表现出高水平的基础相似性（基础单一化），且与人类一样，会根据协调激励调节其行为相似性（战略单一化）。尽管LLM在采取相似行动时协调表现极佳，但在分歧被奖励时，其维持多样性能力不及人类。
原文摘要 · Abstract (English)
AI agents increasingly operate in multi-agent environments where outcomes depend on coordination. We distinguish primary algorithmic monoculture -- baseline action similarity -- from strategic algorithmic monoculture, whereby agents adjust similarity in response to incentives. We implement a simple experimental design that cleanly separates these forces, and deploy it on human and large language model (LLM) subjects. LLMs exhibit high levels of baseline similarity (primary monoculture) and, like humans, they regulate it in response to coordination incentives (strategic monoculture). While LLMs coordinate extremely well on similar actions, they lag behind humans in sustaining heterogeneity when divergence is rewarded.
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。