Agents
The Butterfly Defects: Tracing Cooperation in LLM Agent Networks
arXiv:2610.32726v1 Announce Type: cross Abstract: As large language models (LLMs) increasingly operate as interconnected agents, a fundamental question emerges: does individual cooperation translate i
arXiv:2610.32726v1 Announce Type: cross 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.
Related
- More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration
- ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiation
- A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
Source: arXiv cs.CL | 2026-10-26