LMSYS's New OPD Training Makes Qwen3.5 Reason 3X Faster with Improved Accuracy
ying11231 · x · 2026-07-23
LMSYS's Miles system has introduced On-Policy Distillation (OPD) as a first-class training primitive. In its first experiment, pure OPD reduced the reasoning length of the Qwen3.5-35B-A3B model by approximately 3X while slightly improving accuracy, without using any task rewards.
Key highlights from the controlled self-distillation run include:
- Accuracy improved: held-out DAPO rose from 0.8457 to 0.8945
- 3X shorter responses: rollout length dropped from 18.6k tokens to 5.5k–6.7k
- Student converged to teacher: reverse-KL fell from 0.045 to 0.010
- Efficient scoring: uses sparse per-position teacher scoring instead of dense O(R²K) payload
- Flexible to use: supports running pure distillation, or OPD combined with GRPO/PPO rewards
Next steps for the team include exploring OPD-augmented RL, scaling studies, and multi-teacher OPD.
More from Research
- Navier-Stokes, Riemann, P vs NP: what this week's math buzzwords mean for you — koltregaskes · 2026-09-11
- Fruit fly connectome LLM weights land on Hugging Face, transformers-compatible — ngxson · 2026-09-11
- Fruit fly brain as an LLM: connectome-driven language model demo goes live — ngxson · 2026-09-11
- Harry Collins: LLMs can't do frontier science because they can't invent new language — whoamisri · 2026-09-11
- The Waymo effect: how AI is quietly making research less collaborative — JohnHammersley · 2026-09-11
- Causal-only attention for non-generative tasks is wasteful, argues HF engineer — antoine_chaffin · 2026-09-11