How a Cooperative-Override Circuit Suppresses Nash Play in Large Language Models.

arXiv:2604.27167v4 Announce Type: replace-cross Abstract: On the named Prisoner's Dilemma under direct prompting, three larger instruction-tuned models, Llama-3-70B, Qwen2.5-32B, and Qwen2.5-72B, lock at full cooperation, the metric's maximum distance from Nas