{"slug": "language-models-that-play-chess-2700-elo-and-explain-their-moves", "title": "Language Models That Play Chess (2700 Elo) and Explain Their Moves", "summary": "Researchers introduced Queen, a 4B-parameter chess-language model that plays at Grandmaster level and explains its moves, gaining over 900 Elo points (1782 to 2697) across seven iterations of training, according to an arXiv paper submitted on 2 Oct 2026. Queen combines a silent expert chess encoder with an instruction-tuned language model via cross-attention and an iterative distillation algorithm using a natural-language analog of the Bellman update. The model surpasses all frontier models on playing strength and puzzle accuracy despite having three orders of magnitude fewer parameters, and LM-based evaluations show its explanations approach GPT-5.6-Sol (high) in coherence.", "body_md": "# Computer Science > Computation and Language\n\n  [Submitted on 2 Oct 2026]\n\n# Title:Language Models that Play Chess and Explain Their Moves\n\n[View PDF](https://arxiv.org/pdf/2610.03695)\n\n[HTML (experimental)](https://arxiv.org/html/2610.03695v1)\n\nAbstract:Modern chess engines are silent experts: they play at a superhuman level, but do not offer explanations for their play. On the other hand, language models (LMs) can generate plausible-sounding explanations, but their weak playing strength limits the utility of their explanations. We introduce Queen, a 4B-parameter chess-language model that can explain its moves and plans while playing at the level of a typical Grandmaster. Our novel framework enables domain-specific reasoning through complementary components: an encoder-decoder architecture and an iterative distillation algorithm. This architecture integrates a silent expert chess encoder with an instruction-tuned LM through cross-attention, which we train via a question-answering curriculum to extract chess concepts from the encoder's representations. Building on this domain-adapted model, we iteratively improve its explanations with a natural-language analog of the Bellman update: the model analyzes the positions after its top candidate moves and consolidates them into an explanation of the current position, which is then distilled back into the model. Over seven iterations, our model gains over 900 Elo points (1782 to 2697), substantially surpassing all frontier models on both playing strength and puzzle accuracy, despite containing three orders of magnitude fewer parameters. Furthermore, LM-based evaluations show that our explanations are fluent and approach GPT-5.6-Sol (high) in coherence. The generality of our architecture and training procedure suggests a recipe for applying language models to domains where silent expert encoders are available, like games, robotics, and computer use.\n    \n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/language-models-that-play-chess-2700-elo-and-explain-their-moves", "canonical_source": "https://arxiv.org/abs/2610.03695", "published_at": "2026-10-06 02:18:39+00:00", "updated_at": "2026-10-06 02:48:59.776379+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "machine-learning", "artificial-intelligence"], "entities": ["Queen", "arXiv", "GPT-5.6-Sol"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/language-models-that-play-chess-2700-elo-and-explain-their-moves", "markdown": "https://wpnews.pro/news/language-models-that-play-chess-2700-elo-and-explain-their-moves.md", "text": "https://wpnews.pro/news/language-models-that-play-chess-2700-elo-and-explain-their-moves.txt", "jsonld": "https://wpnews.pro/news/language-models-that-play-chess-2700-elo-and-explain-their-moves.jsonld"}}