arxiv:2609.14708
Published on Sep 13
· Submitted by
Yecheng Wu on Sep 15
Upvote
3
Authors:
,
Abstract
Lightning Weave composes independently trained reasoning capabilities into a single efficient student via on-policy distillation, improving both accuracy and token efficiency across math and code benchmarks.
Generated by thinkingmachines/Inkling-Small
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-training to the resulting specialist. Lightning Weave combines aligned log-ratio shifts at shared student token states and uses Tilted-Target DOPD to convert the cached signals into a stable learning target. Each anchor pair scores the cached trajectories once, enabling subsequent student training without serving multiple live anchor models concurrently. Across diverse student models and benchmarks in mathematics and code, Lightning Weave substantially improves upon the base students and achieves a state-of-the-art accuracy-efficiency frontier. 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 response tokens. Adjusting the relative strengths of the anchor signals yields a strong empirical accuracy-efficiency Pareto frontier. These results establish Lightning Weave as a new practical route to efficient reasoning through capability composition. Code will be released soon.
View arXiv page View PDF Add to collection
Community
Paper author Paper submitter 7 days ago
Lightning Weave improves the accuracy-efficiency frontier of large reasoning models by composing policy shifts from accuracy- and efficiency-oriented teachers into a single student through offline distillation.
7 days ago
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
-
RISE: Recursive Improvement via Self-Extrapolating Policy Distillation (2026)
-
Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold (2026)
-
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation (2026)
-
WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training (2026)
-
Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms (2026)
-
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on HF Mirror checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
· Sign up or log in to comment
Upvote
3
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2609.14708 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2609.14708 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2609.14708 in a Space README.md to link it from this page.