Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition
Lightning Weave composes capabilities from independently post-trained models via on-policy distillation, improving Qwen3.5-4B reasoning accuracy while cutting tokens.
Lightning Weave is a post-training framework that merges accuracy and efficiency capabilities from independently post-trained specialist models into a single student via on-policy distillation. Each capability is represented as a policy shift, combined via aligned log-ratio shifts and Tilted-Target DOPD, enabling training without serving multiple live anchor models concurrently. On Qwen3.5-4B, it raises HMMT 2025 accuracy from 59.2% to 64.0% with 10.7% fewer response tokens, and LiveCodeBench v5 accuracy from 41.7% to 54.2% with 9.6% fewer tokens. The authors report a state-of-the-art accuracy-efficiency Pareto frontier across diverse students and math/code benchmarks, with code planned for release.
- Composes capabilities from independently post-trained anchor models into one student via on-policy distillation
- Qwen3.5-4B: HMMT 2025 59.2% to 64.0% with 10.7% fewer tokens; LiveCodeBench v5 41.7% to 54.2%
- Tilted-Target DOPD converts cached log-ratio shifts into stable targets without live anchor serving
- Achieves state-of-the-art accuracy-efficiency Pareto frontier across math and code benchmarks
From the original article
1 min read at huggingface.co
A core goal of efficient reasoning is to improve the accuracy-efficiency frontier. However, jointly improving reasoning accuracy and inference efficiency can be challenging, as the two objectives can favor different reasoning behaviors. Independently post-trained models already offer distinct strengths in accuracy and efficiency.
By Yecheng Wu, Song Han, Han Cai · huggingface.co
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.