LLMs for Game Theory: Entropy-Guided In-Context Learning and Adaptive CoT Reasoning
arXiv:2601.10775v2 Announce Type: replace
Abstract: We propose a novel LLM-based framework for reasoning in discrete, game-theoretic tasks, illustrated with \emph{Tic-Tac-Toe}. The method integrates in-context learning with entropy-guided chain-of-tho…