AI RESEARCH
Scheming Ability in LLM-to-LLM Strategic Interactions
arXiv CS.AI
•
ArXi:2510.12826v2 Announce Type: replace-cross As large language model (LLM) agents are deployed autonomously in diverse contexts, evaluating their capacity for strategic deception becomes crucial. While recent research has examined how AI systems scheme against human developers, LLM-to-LLM scheming remains underexplored. We investigate the scheming ability and propensity of frontier LLM agents through two game-theoretic frameworks: a Cheap Talk signaling game and a Peer Evaluation adversarial game.