Improving Code Localization with Repository Memory

By Boshi Wang, Weijian Xu, Yunsheng Li, Mei Gao, Yujia Xie, Huan Sun, Dongdong Chen. 2025

Subfields: LLM Agents & Tool Use, Program Analysis & Verification, Software Engineering

Citations in the corpus

• A^2Agent: Action-Aware Reinforcement Learning for Repository-Level Code Localization Agents (2026, unknown): “…through graph modeling, symbol tracing, terminal navigation, and commit history (Chen et al., 2025; Zhang et al., 2025; Sutawika et al., 2026; Wang et al., 2025a; Jiang et al., 2025), while pipeline-based methods such as Agentless (Xia et al., 2024) take a complementary route by decomposing…”
• Agentic Software Issue Resolution with Large Language Models: A Survey (2025, unknown): “Wang et al. [153] and LocAgent [32] also incorporate this method.”