SPSD Paper: Self-Play Search Distillation Boosts LLM Reasoning
Edinburgh researchers' SPSD framework distills MuZero-style self-play search from board games into superhuman chain-of-thought, lifting LLM math scores from 24.1 to 36.6.
2026-09-29 ~ 2026-09-30 · 3 related posts
- SPSD distills MuZero self-play search into LLM reasoning traces, math jumps 24.1→36.6 — PMinervini · 2026-09-29
- Self-play on board games distills superhuman CoT, lifting Qwen3-4B math average from 24.1 to 36.6 — PMinervini · 2026-09-29
- SPSD distills self-play search records into superhuman CoT, lifting Qwen3-4B math scores — Lorenzo Molfetta · 2026-09-30