cs.CLNov 6, 2026

Failure Profiling and Reachable Trajectory Selection for Reasoning Distillation

Authors: Yijun Zhu, Jianxin Wang, Chengchao Shen

Organizations: School of Computer Science and Engineering, Central South University

Abstract

Training smaller language models on reasoning solutions generated by a larger teacher model is the prevailing approach for transferring mathematical reasoning capabilities. However, the student tends to overfit the output distribution of the teacher and generalizes poorly when its own behavior at inference time deviates from the training data. Recent methods attempt to bridge this gap by incorporating error data, yet the corrective trajectories still reflect the reasoning patterns of the teacher, which the student cannot reliably reproduce, leaving the distribution mismatch largely unresolved. We propose a method, Failure Profiling and Reachable Trajectory Selection (FPRT), built on the insight that effective training data should be jointly determined by what the student fails on and what it can realistically learn. Our method first profiles the failure behavior of the student on each problem through repeated sampling, characterizing it in terms of error rate and error consistency to reveal qualitatively distinct failure modes. Each mode demands a fundamentally different training signal. The diagnosed mode then guides candidate generation from the teacher via distinct prompting strategies tailored to each failure type. Among the correct candidates, our method selects the one whose initial reasoning steps after the point of divergence are most reproducible by the student. These first corrective steps constitute the primary bottleneck, while the remaining steps follow an already corrected context and can therefore be continued more readily. This contrasts with standard reranking approaches, which score the trajectory as a whole and thereby dilute the signal at the critical reasoning transition. Experiments demonstrate that our method achieves the SOTA performance across the five benchmarks on both student backbones.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Distribution Corrected Offline Data Distillation for Large Language Models

    May 13, 2026Yumeng Zhang, Zhengbang Yang, Yevin Nikhel Goonatilake +1CoT DistillationOnline Knowledge Distillation

  2. The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning

    Sep 29, 2026Matthieu Zimmer, Xiaotong Ji, Tu Nguyen +1Language Model DistillationCoT Distillation

  3. From Solver Trajectories to Teaching Trajectories: Cognition-Aligned Reasoning Distillation

    Oct 27, 2026Yashuo Luo, Qianren Mao, Ziqi Qin +6Reasoning DistillationLanguage Model Distillation