Work

RepoDistill: Distilling Repository Knowledge through Compression-Aware Budget Allocation and Policy Optimization

Year: 2026

Type: conference-paper

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 similaritybased and graph-based approaches, can identify relevant code snippets, they often retrieve excessive contexts that intensify the "lost-inthe-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-andplay 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 Long-CodeU.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-6CE3/.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.217