frontier models
A Four-Billion-Parameter Model Played Grandmaster Chess and Explained It
Queen joins a silent chess encoder to a language model and iteratively distills post-move analysis.
Summary
Queen joins a silent chess encoder to a language model and iteratively distills post-move analysis.
Queen uses cross-attention to connect a chess expert encoder with an instruction-tuned language model, then improves explanations through a natural-language analogue of a Bellman update. Across seven iterations, the authors report its playing strength rising from 1782 to 2697 Elo. Fluency evaluations approached a frontier model, but explanation quality remains model-judged rather than a proof of faithful reasoning.
Why it matters
Queen joins a silent chess encoder to a language model and iteratively distills post-move analysis.
Limits and context
No additional limitation was separately recorded.
Key claims
Queen joins a silent chess encoder to a language model and iteratively distills post-move analysis.
Evidence: source-2026-10-05-009
Sources
- arXiv preprint 2610.03695arXiv · primary research
Corrections
No corrections have been recorded for this story.