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 \textbf{FuseSearch}, reformulating parallel code localization as a \textbf{joint quality-efficiency optimization} task. Through defining \textbf{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 $F_1$ 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：代码定位是自动化软件开发流程中的关键瓶颈。虽然并发工具执行能够提升发现速度，但现有智能体存在34.9%的冗余调用率，抵消了并行化优势。我们提出\textbf{FuseSearch}方法，将并行代码定位重新定义为\textbf{质量-效率联合优化}任务。通过定义\textbf{工具效率}——即独特信息增益与调用次数的比值——我们采用监督微调与强化学习两阶段训练策略来学习自适应并行执行机制。与固定搜索宽度的传统方法不同，FuseSearch能够依据任务上下文动态调节搜索广度，实现从探索阶段到精炼阶段的演进。在SWE-bench Verified基准测试中，FuseSearch-4B模型在取得最先进性能（84.7%文件级与56.4%函数级$F_1$分数）的同时，实现93.6%的加速效果，调用轮次减少67.7%，令牌消耗降低68.9%。实验结果表明，通过消除噪声冗余信号，效率导向的训练机制能够自然提升定位质量，从而构建高性能、低成本的代码定位智能体。