# How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess Source: [How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess]() Collection index: [llms.txt]() Data updated: 2026-05-06T05:00:03.989Z Authors: Lucas Dionisopoulos, Nicklas Majamaki, Prithviraj Ammanabrolu Published: 2026-04-06T19:53:39.000Z ## Abstract We study how reasoning evolves in a language model -- from supervised fine-tuning (SFT) to reinforcement learning (RL) -- by analyzing how a set of theoretically-inspired datasets influences language model performance in chess. We find that fine-tuning a model to directly predict the best move leads to effective RL and the strongest downstream performance -- however, the RL stage elicits \\textit{unfaithful} reasoning (reasoning inconsistent with the chosen move). Alternatively, training on multi-move trajectories yields comparable downstream performance with faithful reasoning and more stable RL. We analyze multiple qualitative and quantitative measures and highlight how these evolve from SFT through RL; we find several SFT-checkpoint metrics -- spanning evaluation performance, hallucination rates, and reasoning quality -- to be predictive of post-RL model performance. Finally, we ground our results with an experiment measuring \\textit{chess information density} in our custom datasets. We release models as well as training data, evaluations, and code that allowed us to surpass leading open-source reasoning models in chess with a 7B-parameter model. Code, models, and data are available at https://github.com/lucasdino/lang-chess. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Predict Move on Predict Move 400 samples](): Predict Move; Predict Move 400 samples; Prediction Move Legal %: 98. - [Legal Moves Prediction on Chess Reasoning Dataset Legal Moves](): Legal Moves Prediction; Chess Reasoning Dataset Legal Moves; IoU: 87. ## Original sources and implementation [Original paper]() [PDF]()