arXiv cs.CL· Maria Sampani, Maria Lymperaiou, Angeliki Dimitriou, Giorgos Filandrianos, Chrysoula Zerva, Giorgos Stamou·· 12 小时前AI 评分34
LLM 智能体网络中的合作行为：The Butterfly Defects 研究
The Butterfly Defects: Tracing Cooperation in LLM Agent Networks
AI 导读
研究通过迭代囚徒困境（IPD）考察开放权重 LLM 从两两互动扩展到同质与异质网络后的合作行为，发现合作高度依赖模型组合与细微的语言变化。与相同同伴合作良好的模型在混合群体中可能转向背叛，一个简单的不确定性提示即可改变合作水平、重新分配成本，并影响相隔数跳的未暴露智能体。甚至颠倒动作标签顺序也会显著改变行为，不确定性框架有时会放大这种敏感性。
正文 · 原文
Abstract:As large language models (LLMs) increasingly operate as interconnected agents, a fundamental question emerges: does individual cooperation translate into collective cooperation? We investigate this question through the Iterated Prisoner's Dilemma (IPD), moving from dyadic interactions to homogeneous and heterogeneous networks of open-weight LLMs. Our findings reveal that cooperation is highly sensitive to model composition and seemingly minor linguistic changes. Models that cooperate with identical peers can shift toward defection in mixed populations. A simple uncertainty cue can increase or decrease cooperation, redistribute costs, and affect unexposed agents several hops away. Even reversing action-label order can dramatically alter behavior, with uncertainty framing sometimes amplifying this sensitivity. Together, these findings challenge the notion of cooperation as a stable model-level property, revealing how strategic behavior depends on interaction partners, network positions, and the language used to frame decisions.
| Subjects: | Physics and Society (physics.soc-ph); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.32726 [physics.soc-ph] |
| (or arXiv:2610.32726v1 [physics.soc-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32726 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Maria Lymperaiou [view email]
[v1]
Fri, 23 Oct 2026 14:46:57 UTC (2,152 KB)
来源：arXiv cs.CL · arxiv.org