{"ID":2895993,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.07495","arxiv_id":"2507.07495","title":"PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving","abstract":"Recently, decomposing complex problems into simple subtasks--a crucial part of human-like natural planning--to solve the given problem has significantly boosted the performance of large language models (LLMs). However, leveraging such planning structures during post-training to boost the performance of smaller open-source LLMs remains underexplored. Motivated by this, we introduce PLAN-TUNING, a unified post-training framework that (i) distills synthetic task decompositions (termed \"planning trajectories\") from large-scale LLMs and (ii) fine-tunes smaller models via supervised and reinforcement-learning objectives designed to mimic these planning processes to improve complex reasoning. On GSM8k and the MATH benchmarks, plan-tuned models outperform strong baselines by an average $\\sim7\\%$. Furthermore, plan-tuned models show better generalization capabilities on out-of-domain datasets, with average $\\sim10\\%$ and $\\sim12\\%$ performance improvements on OlympiadBench and AIME 2024, respectively. Our detailed analysis demonstrates how planning trajectories improves complex reasoning capabilities, showing that PLAN-TUNING is an effective strategy for improving task-specific performance of smaller LLMs.","short_abstract":"Recently, decomposing complex problems into simple subtasks--a crucial part of human-like natural planning--to solve the given problem has significantly boosted the performance of large language models (LLMs). However, leveraging such planning structures during post-training to boost the performance of smaller open-sou...","url_abs":"https://arxiv.org/abs/2507.07495","url_pdf":"https://arxiv.org/pdf/2507.07495v1","authors":"[\"Mihir Parmar\",\"Palash Goyal\",\"Xin Liu\",\"Yiwen Song\",\"Mingyang Ling\",\"Chitta Baral\",\"Hamid Palangi\",\"Tomas Pfister\"]","published":"2025-07-10T07:30:44Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}