QUEEN paper distills AlphaZero-style chess search into language for LLMs
danqi_chen · x · 2026-10-07
A PhD researcher's paper QUEEN gets LLMs to play strong chess and explain it — by not teaching the model chess from text. Instead it connects a strong silent expert (search) to language, repeatedly converts search into explanations, and distills those back into the model, described as a natural-language analogue of AlphaZero with both architectural and algorithmic innovation.
Commenters note the idea generalizes: robotics, computer use, theorem proving, and scientific simulators already have experts that know more than they can say — give the expert a mouth, then teach the mouth to think with it.
Related event: Princeton's QUEEN: 4B Chess-Language Model Reaches Grandmaster Level(7 posts)→
More from Research
- Looped transformers are trending again, tracing roots back to a 2016 paper — natanielruizg · 2026-10-07
- Fixed token codes suffice: 1.7B LM trains without a trainable input embedding table — A. Bochkov · 2026-10-07
- EmbeddingGemma 2 hands-on: 740M multimodal embeddings for search and RAG, runnable on a free T4 — Prompt Engineering · 2026-10-07
- Isomorphic, DeepMind and Meta join DOE-NIH partnership to build an AI model of the cell — snikolov · 2026-10-07
- Bi-manual mobile UMI demo unlocked for robot manipulation data collection — neurosp1ke · 2026-10-07
- Researcher presents Meta-Harness and Combee at COLM 2026, seeks industry roles — Kangwook_Lee · 2026-10-07