Author

Canhui Wu

h-index 2 View on Semantic Scholar

We have 2 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning

Experiments show that GRIP achieves a better accuracy-efficiency trade-off than fixed or search-based merging baselines and further reveals module-wise fusion patterns associated with efficient reasoning.

Lam So, Canhui Wu, Han Lin · 0 citations

Preprint Aug 2026

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents

FailForge is proposed, an agentic framework that converts failed rollouts into training signal, and recovers over 26% of previously failed instances at marginal additional cost, and training Qwen3.5-4B on the augmented corpus improves the SWE-bench Verified resolve rate by 6.6 points over a strong RFT baseline.

Dongyi Lv, E. Fushun, Aichen Cai et al. · 1 citation