Code localization constitutes a key bottleneck in automated software development pipelines. While concurrent tool execution can enhance discovery speed, current agents demonstrate a 34.9% redundant invocation rate, which negates parallelism benefits. We propose FuseSearch, reformulating parallel code localization as a joint quality-efficiency optimization} task. Through defining tool efficiency -- the ratio of unique information gain to invocation count -- we utilize a two-phase SFT and RL training approach for learning adaptive parallel strategies. Different from fixed-breadth approaches, FuseSearch dynamically modulates search breadth according to task context, evolving from exploration phases to refinement stages. Evaluated on SWE-bench Verified, FuseSearch-4B achieves SOTA-level performance (84.7% file-level and 56.4% function-level F1 scores) with 93.6% speedup, utilizing 67.7% fewer turns and 68.9% fewer tokens. Results indicate that efficiency-aware training naturally improves quality through eliminating noisy redundant signals, enabling high-performance cost-effective localization agents.

翻译：代码定位构成自动化软件开发生命周期的关键瓶颈。尽管并发工具执行可提升发现速度，但现有智能体存在34.9%的冗余调用率，这抵消了并行化带来的效益。我们提出FuseSearch，将并行代码定位重构为质量-效率联合优化任务。通过定义工具效率——即单位信息增益与调用次数的比值——我们采用两阶段监督微调与强化学习训练方法，学习自适应并行策略。与固定广度方法不同，FuseSearch根据任务上下文动态调节搜索广度，从探索阶段平滑过渡至精炼阶段。在SWE-bench Verified基准测试中，FuseSearch-4B实现了当前最优性能（文件级F1分数84.7%，函数级F1分数56.4%），同时获得93.6%的加速比，调用轮次减少67.7%，令牌消耗降低68.9%。结果表明，效率感知训练通过消除冗余噪声信号，可自然提升定位质量，从而构建高性能且经济高效的代码定位智能体。