The paper proposes a method that mimics human cognition to train reinforcement learning agents to generate explainable strategies and policies as executable procedures derived from sequences of gameplay actions. It demonstrates automatic learning of such programs for chess and a grid‑based environment, showing that the resulting strategies produce effective actions and can be learned from gameplay data.
By Abhijeet Krishnan, Colin M. Potts, Arnav Jhala, Harshad Khadilkar, Shirish Karande, Chris Martens
As part of learning to play complex games, human players develop develop abstractions for concepts and strategies of gameplay consistent with game rules to improve their performance. These concepts ar...
arXiv:2607. 27574v1 Announce Type: new Abstract: Activation steering has emerged in large language models as a lightweight alternative for dynamically changing a model's behavior at inference time.
By Yoann Poupart, Aur\'elie Beynier, Nicolas Maudet
The paper introduces an automatic metric for evaluating chess explanations based on chess-engine evaluations and finds that current language models perform poorly, relying on surface-level observations. It presents BinProp, a training-free method that helps models discover reusable chess concepts, significantly improving explainability across multiple models. BinProp also generalizes to other board games such as Go, draughts, and shogi without extra tuning.
By Ori Press, Alexander Golubev
arXiv:2607. 00190v1 Announce Type: cross Abstract: Recent advances in reinforcement learning have produced superhuman agents across a wide range of competitive games.
By Andrzej Bia{\l}ecki, Adam Mastalerz, Han Zhou
The paper presents a systematic mapping of recent chess research involving humans, engines, neural and reinforcement‑learning systems, large language models (LLMs), and hybrid approaches. It identifies 84 core study families and classifies them by agent type, strategic‑reasoning stages, and evaluation dimensions, highlighting a strong focus on situation assessment, evaluation, and action selection while noting gaps in planning, explanation, metacognition, and human–AI collaboration. The study also distinguishes hybrid systems by integration timing and cautions that improved human performance in evaluations does not automatically imply human–AI synergy.
By Paolo Ciancarini, Remo Pareschi