SOURCE-LINKED INTELLIGENCE

A^2Agent: Action-Aware Reinforcement Learning for Repository-Level Code Localization Agents

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Localizing issue-relevant code regions is a critical step in automated software engineering. However, due to their reliance on sparse trajectory-level signals, existing methods cannot identify which per-turn actions are effective and often discover correct code regions during exploration but fail to commit them. To address these limitations, we propose an action-aware reinforcement learning method that combines a per-turn reward sequence rewarding both the discovery and commitment of gold code regions with an action-level advantage estimation scheme that isolates each action's credit by groupi

Read original source ↗ Open in workspace

recordType

paper

region

Global