[2603.20510] Grounded Chess Reasoning in Language Models via Master Distillation

Computer Science > Artificial Intelligence arXiv:2603.20510 (cs) [Submitted on 20 Mar 2026] Title:Grounded Chess Reasoning in Language Models via Master Distillation Authors:Zhenwei Tang, Qianfeng Wen, Seth Grief-Albert, Yahya Elgabra, Blair Yang, Honghua Dong, Ashton Anderson View a PDF of the paper titled Grounded Chess Reasoning in Language Models via Master Distillation, by Zhenwei Tang and 6 other authors View PDF HTML (experimental) Abstract:Language models often lack grounded reasoning capabilities in specialized domains where training data is scarce but bespoke systems excel. We introduce a general framework for distilling expert system reasoning into natural language chain-of-thought explanations, enabling compact models to acquire domain expertise and the ability to generate faithful, grounded explanations. Rather than distilling only final outputs, we capture the full reasoning process, transforming opaque expert computations into transparent, step-by-step explanations. We demonstrate this approach in chess, a canonical reasoning domain where language models continue to underperform. Our 4B parameter model, C1, advances from a near-zero baseline to 48.1% accuracy, outperforming all open-source models and most frontier proprietary systems. Notably, C1 surpasses its distillation teacher and generates solutions in two orders of magnitude fewer tokens than baselines. Unlike prior neural chess approaches that predict only best moves, C1 generates explainable solution...