cs.AINov 11, 2026

Same Task, Different Statement: When and How Reformulation Helps LLM Problem Solving

Authors: Wentao Zhang, Xiaoyu Zhang, Chengwei Liu, Yutao Hu, Tao Zhang, Junsheng Wu, Hongping Gan, Yang Liu

Organizations: Northwestern Polytechnical University · CCDS, Nanyang Technological University · Nankai University · Huazhong University of Science and Technology

Abstract

When people face a hard problem, they often restate it in a clearer way before solving it. We study whether the same habit helps large language models by rewriting the statement of a problem. A legal rewrite must keep the meaning, the constraints, and the correct answer unchanged. We test three kinds of rewrites. Decomposition makes hidden subgoals explicit. Typed Reformulation casts the task into a more suitable solving frame. Concept Reduction removes surface detail and exposes the task structure. We evaluate them on eight math, logic, and code benchmarks with eight models, all under the same chain-of-thought solving prompt. The effect is large but depends on the problem type. An oracle that picks the best rewrite after the fact raises accuracy by +27.6% on average. Yet no single rewrite helps every problem, and a mismatched rewrite can hurt. Still, the effect follows clear patterns. Each kind of rewrite fits certain problem types. A simple fixed rule learned from one set of problems transfers part of the gain to new problems. It gains +11.0% on the problems it chooses to rewrite, while blind rewriting loses 5.6% on a similar share of problems. Rewriting is therefore not a universal way to solve problems. The question is when and how to rewrite.

Figures & tables

Explore similar work

CardsList
  1. RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving

    Aug 30, 2026Xiyuan Zhou, Zhuoqi Li, Xinlei Wang +6Mathematical Reasoning BenchmarksLLM Mathematical Reasoning

  2. TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter

    Jul 17, 2026Oliver Savolainen, Emanuele Bastianelli, Hosein AzarbonyadAutomatic Prompt OptimizationLanguage Model Post-Training