SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training

ArXi:2603.07927v1 Announce Type: cross Large language models (LLMs) have transformed the software engineering landscape. Recently, numerous LLM-based agents have been developed to address real-world software issue fixing tasks. Despite their state-of-the-art performance, Despite achieving state-of-the-art performance, these agents face a significant challenge: \textbf{Insufficient high-quality issue descriptions.} Real-world datasets often exhibit misalignments between issue descriptions and their corresponding solutions.