@inproceedings{xiong-etal-2025-think,
    title = "Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair",
    author = "Xiong, Bojian  and
      Lei, Yikun  and
      Liu, Xikai  and
      Zhang, Shaowei  and
      Zhu, Pengyun  and
      Liu, Yan  and
      Leng, Yongqi  and
      Shi, Ling  and
      Zhong, Meizhi  and
      Zhang, Yurong  and
      Gao, Yan  and
      Yiwu  and
      Hu, Yao  and
      Xiong, Deyi",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.109/",
    pages = "1555--1566",
    ISBN = "979-8-89176-333-3",
    abstract = "Large language models usually suffer from multiple-file coding scenarios where strong inter-file dependencies manifest, typically demonstrated in SWE-bench. To mitigate this issue, we propose Think-Search-Patch (TSP), a retrieval-augmented reasoning framework for repository-level code repair. At the Think stage, our system breaks down a coding task and creates clear search query. Next, at the Search stage, it retrieves relevant code snippets using models like E5. At the final Patch stage, it generates standardized patches based on the key snippets. In addition the proposed framework, we enhance system reliability through a two-stage training process. At the first stage, the system undergoes supervised fine-tuning (SFT) on our TSP dataset. At the subsequent stage, we employ rejection sampling with correction to generate preference pairs for Direct Preference Optimization (DPO) training, thereby reducing errors in the intermediate phases. Experimental results demonstrate that TSP framework enhances retrieval accuracy and repair success on SWE-bench Lite, even surpassing models with a larger size in managing extensive code contexts and successfully addressing bugs spanning across multiple files. All data and code available at https://github.com/Gengar0215/TSP-framework."
}