A^2Agent：面向仓库级代码定位智能体的动作感知强化学习方法
A^2Agent: Action-Aware Reinforcement Learning for Repository-Level Code Localization Agents
- College of Computing and Informatics（计算与信息学院）
- Sungkyunkwan University（成均馆大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
A^2Agent是一种动作感知强化学习方法，通过优化奖励与优势估计，在SWE-Bench的两个基准上提升代码定位性能，且4B模型优于更大规模的基线。
AI中文摘要：
定位与问题相关的代码区域是自动化软件工程的关键步骤。然而，现有方法依赖稀疏的轨迹级信号，无法识别每一轮动作的有效性，且常在探索过程中发现正确代码区域却无法提交。为解决这些局限，我们提出一种动作感知强化学习方法，结合每轮奖励序列（奖励发现与提交正确代码区域）与动作层面优势估计方案（通过分组共享相同探索上下文的轮次，隔离每个动作的贡献）。大量评估表明，该方法在SWE-Bench Verified上的平均F1值较现有最优方法（SOTA）提升1.58%，在SWE-Bench Pro上提升8.55%；我们的4B模型性能优于规模大至8倍的基线模型。代码可在指定URL获取。
英文摘要：
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 grouping turns sharing the same exploration context. Extensive evaluations show that our method improves the average F1 over the state-of-the-art (SOTA) by 1.58% on SWE-Bench Verified and 8.55% on SWE-Bench Pro, with our 4B model outperforming baselines up to 8x larger. Our code is available at https://github.com/donian00/A2Agent.
