@inproceedings{yin-etal-2026-repodistill,
    title = "{R}epo{D}istill: Distilling Repository Knowledge through Compression-Aware Budget Allocation and Policy Optimization",
    author = "Yin, Xin  and
      Ding, Zixiang  and
      Zhang, Yiang  and
      Wang, Qiang  and
      Wang, Rui  and
      Ni, Chao  and
      Cui, Zhe",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.217/",
    pages = "4425--4443",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs) have achieved strong performance on many code-related tasks, yet they still struggle with repository-level scenarios where reasoning depends on long, noisy, and structurally complex contexts. While existing retrieval methods, including both similarity-based and graph-based approaches, can identify relevant code snippets, they often retrieve excessive contexts that intensify the ``lost-in-the-middle'' phenomenon and dilute model attention with redundant contexts. To address this, we present RepoDistill, a novel framework that integrates retrieval with learned budget allocation for fine-grained context compression. RepoDistill first employs a plug-and-play lightweight GraphRAG to retrieve context that follows logical flows. It then applies Compression-Aware Budget Allocation guided by Compression-Aware Policy Optimization, which formulates context management as a multi-step decision problem and learns allocation policies for contexts. Experiments show that RepoDistill outperforms baselines, achieving gains of up to +7.00 on SWE-QA, +24.4{\%} on CoderEval, and +0.25 on LongCodeU. Furthermore, a compact 4B-parameter model trained with RepoDistill can serve as an effective context compressor for closed-source LLMs, reducing input tokens by up to 66{\%} while maintaining comparable performance. We release our code at https://anonymous.4open.science/r/RepoDistill-12B0."
}