@inproceedings{parmar-etal-2025-plan,
    title = "{PLAN}-{TUNING}: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving",
    author = "Parmar, Mihir  and
      Goyal, Palash  and
      Liu, Xin  and
      Song, Yiwen  and
      Ling, Mingyang  and
      Baral, Chitta  and
      Palangi, Hamid  and
      Pfister, Tomas",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1087/",
    pages = "21430--21444",
    ISBN = "979-8-89176-332-6",
    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 {\textasciitilde}7{\%}. Furthermore, plan-tuned models show better generalization capabilities on out-of-domain datasets, with average {\textasciitilde}10{\%} and {\textasciitilde}12{\%} 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."
}