arxiv
PublishedSeptember 21, 2026 at 4:00 AM
How a Cooperative-Override Circuit Suppresses Nash Play in Large Language Models
Publisher summary· verbatim
arXiv:2604.27167v3 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 Nash with zero variance across replicates,
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivLoRA Enhanced Contrastive Learning with SAS Vision Transformers7harxivHallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency7harxivTatBLiMP: A Benchmark of Linguistic Minimal Pairs for Tatar7harxivRuntime Authorization for Resources Acquired by AI Agents7hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗