Skip to content
Search
paperAugust 2026Unreviewed

Humans Are More Diverse: Frontier LLMs Show Extreme Policies in Idealised AI Development Races

Phu Hoa Pham, Duy Minh Dao Sy, Trung Kiet Huynh, Phu Quy Nguyen Lam, Chi Nguyen Tran, Minh Trung Le, Phong Hao Le, Dinh Nam Nguyen, Thien Ky Nguyen Dong, Elias Fernandez Domingos, Le Hong Trang, The Anh Han

View resourcePDF

Abstract

An AI development race creates a multi-agent safety dilemma. Each company can develop slowly and safely, or move faster while taking a risk that may remove its final reward. We use this repeated game to study strategic safety behaviour among large language model (LLM) agents in races with two to five players. However, a valid action does not show that an agent understands the game. We therefore place an audit gate before behavioural interpretation. We first verify the game engine, then test rule

Categories

Agent Architecture

Cite

@misc{pham2026humans,
  title = {{Humans Are More Diverse: Frontier LLMs Show Extreme Policies in Idealised AI Development Races}},
  author = {Phu Hoa Pham and Duy Minh Dao Sy and Trung Kiet Huynh and Phu Quy Nguyen Lam and Chi Nguyen Tran and Minh Trung Le and Phong Hao Le and Dinh Nam Nguyen and Thien Ky Nguyen Dong and Elias Fernandez Domingos and Le Hong Trang and The Anh Han},
  year = {2026},
  month = aug,
  eprint = {2608.01193},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.01193}
}