Search papers, labs, and topics across Lattice.
This paper introduces PhoenixRepair, a multi-agent framework designed to enhance the exploration of repair strategies in automated issue resolution by systematically sampling multiple candidate edit locations and iteratively refining patch generation. By addressing the limitations of existing agent-based methods, PhoenixRepair significantly expands the search space for potential repairs, leading to improved fault localization and higher resolution rates. Experiments demonstrate that PhoenixRepair outperforms previous methods, achieving a 7.8% relative improvement and a 76.0% Pass@1 resolution rate on benchmark tasks.
PhoenixRepair redefines how software agents explore repair strategies, achieving a 76% resolution rate by leveraging multi-location sampling and iterative refinement.
While Large Language Models have greatly advanced automated issue resolution, existing agent-based methods exhibit a fundamental limitation in their insufficient exploration of repair strategies. This insufficiency manifests in two key aspects. First, the exploration of multiple potential edit locations is limited. Second, the exploration of repair attempts at each location is also insufficient. To address these challenges, we present PhoenixRepair, a multi-agent framework that systematically explores multiple candidate edit locations and performs iterative reflection and refinement on patch generation, thereby expanding the search space of repair strategies. Our framework begins with multi-location sampling, optionally augmented with graph-based localization information for difficult tasks, followed by iterative reflection and refinement to generate better patches, culminating in final-round generation guided by distilled insights from all historical attempts. Experiments on SWE-bench-Verified demonstrate that PhoenixRepair achieves the largest relative improvement of 7.8\% over SWE-agent under DeepSeek-V3.1, and attains the highest resolved rate of 76.0\% Pass@1 under MiniMax-M2.5. Meanwhile, it achieves higher fault localization accuracy than existing approaches. Our code is available at https://github.com/DeepSoftwareAnalytics/PhoenixRepair.
