FastContext：用于编码智能体的高效仓库探索子智能体
阅读原文· arxiv.orgFastContext 是一个将仓库探索与任务解决相分离的专用探索子智能体，由 4B–30B 参数的探索模型驱动，通过参考模型轨迹和任务奖励进行优化。集成 FastContext 的 Mini-SWE-Agent 在 SWE-bench Multilingual、SWE-bench Pro 和 SWE-QA 基准上端到端解决率提升最多 5.5%，同时编码智能体 token 消耗减少最多 60%，且边际开销很低。结果表明，仓库探索可与解决任务分离，并由专用模型高效处理。
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