SOURCE-LINKED INTELLIGENCE
Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition
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. We introduce Lightning Weave, a post-training framework that extracts and composes these independently learned capabilities in a single student through on-policy distillation. Each acquired capability is represented by the policy shift from the model before post-train
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-13T18:05:58.000Z
First collected: 2026-09-20T12:21:05.240Z. This is not the publication date.