给AI配个专职探路员，省60%算力
现在的AI写代码助手有个通病：它一边要翻仓库找文件，一边要写代码，结果翻文件时读到的无关内容会污染它的思路，还浪费大量算力。微软这篇论文的做法很直接——给AI配一个专职的“探路子模型”，只负责快速定位代码位置，不参与写代码。这个探路员能并行搜索，返回精确的文件路径和行号，把主模型从翻仓库的杂活里解放出来。在多个编程基准测试上，这套方案让修复成功率最高提升5.5%，同时主模型消耗的token减少60%。它不是你明天就能用的工具，但指明了一个方向：把大模型的任务拆成“找”和“做”两个角色，比让一个模型干所有事更聪明。
📄 原文摘要(英文)
Large Language Model (LLM) coding agents have achieved strong results on software engineering tasks, yet repository exploration remains a major bottleneck: locating relevant code consumes substantial token budget and pollutes the agent's context with irrelevant snippets. In most agents, the same model explores the repository and solves the task, leaving exploratory reads and searches in the solver's history. We present FastContext, a dedicated exploration subagent that separates repository exploration from solving. Invoked on demand, FastContext issues parallel tool calls and returns concise file paths and line ranges as focused context. FastContext is powered by specialized exploration models spanning 4B--30B parameters. We bootstrap them from strong reference-model trajectories and refine them with task-grounded rewards for broad first-turn search, multi-turn evidence gathering, and precise citation generation. Across SWE-bench Multilingual, SWE-bench Pro, and SWE-QA, integrating FastContext into Mini-SWE-Agent improves end-to-end resolution rates up to 5.5\% while reducing coding-agent token consumption up to 60\%, with marginal overhead. These results show that repository exploration can be separated from solving and handled effectively by specialized models. Code and data: https://github.com/microsoft/fastcontext