作者位次 #4/7ACL 2026Findings· Findings of ACL
R epo D istill: Distilling Repository Knowledge through Compression-Aware Budget Allocation and Policy Optimization
Xin Yin · Zixiang Ding · Yiang Zhang · Qiang Wang · Rui Wang · Chao Ni · Zhe Cui
摘要
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-...