Skip to content
NewA calmer, faster ZeroHour

Self-Play Search Distillation for Large Language Model Reasoning

Hugging Face daily papersby Lorenzo Molfetta, Wai-Chung Kwan, Giacomo Frisoni ()1 min read4 · 2 reads
AI summary · grok-4.7Summaries by Vani AI

Self-play search distillation raises Qwen3-4B-Base's math benchmark mean from 24.1 to 36.6.

Self-Play Search Distillation generates synthetic reasoning data from MuZero-like networks trained by self-play on board games. At each state the search record names a preferred decision, plausible alternatives, opponent replies, and value estimates, which are converted into environment-grounded chains of thought. Although trained only on those game records, Qwen3-4B-Base raises its mean over six mathematics benchmarks from 24.1 to 36.6 and its held-out-game win rate from 15% to 45%. The authors present SPSD as an annotation-efficient alternative to low-quality synthetic data and costly human labels.

Key facts
  • SPSD turns MuZero-like self-play search into chain-of-thought supervision.
  • Qwen3-4B-Base mean score on six math benchmarks rises from 24.1 to 36.6.
  • Held-out game win rate increases from 15% to 45%.
  • Training uses only game search records yet transfers to unseen mathematics.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at huggingface.co

Improving reasoning abilities in Large Language Models (LLMs) requires high-quality data that exposes difficult decisions, competing alternatives, and their consequences. Data scarcity is driven by the low quality of synthetic data and the cost of human labeling.

Hugging Face daily papers

By Lorenzo Molfetta, Wai-Chung Kwan, Giacomo Frisoni · huggingface.co

Read the full article at Hugging Face daily papers

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.