7B搜索器先看仓库再路由，SWE-bench Pro追平最强模型，成本降五分之一，换新修复模型不用重训。
SuperScout 先用 7B 的 SuperScout-7B 搜索代码仓库，生成经过沙箱验证的交接报告，再由路由器把任务分给四个前沿修复模型。在 SWE-bench Pro 的 Python 切片（266 个任务）官方预算档下，SuperScout 解决 159 个，最佳单模型解决 158 个，单次解决总成本约为后者的五分之一。在同一个 266 任务的 SWE-bench Pro 上，去掉路由器、只用最便宜修复模型加交接报告，成绩与路由系统并列，说明交接报告而非路由决策带来了成绩。配对校准研究（N=99）显示，交接报告让三个较便宜修复模型提升、最强模型略降，但各修复模型效应仅有方向性；搜索器的隐藏状态改善了成本路由，而交接报告文本本身没有。SuperScout-7B 的搜索计算在每个任务上只增加不到半美分 GPU 时间。
Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First
Frontier language models can resolve repository-level software issues, but each attempt is expensive, and existing routers select a model from the issue text alone. We present SuperScout, which routes after scouting the repository: a 7B searcher, SuperScout-7B, first explores the repository and produces a structured handoff whose reproduction claims are sandbox-verified, with false claims stripped before delivery. The searcher's hidden states, together with the task text, then feed a resume-based router that dispatches the task to one of four frontier fixers. Adding a new fixer requires no retraining. On the full Python slice of SWE-bench Pro (266 tasks) under the benchmark's official capped budget tier, SuperScout matches the best single model's solve rate (159 of 266 for SuperScout, 158 for the best model) at about a fifth of the total cost per solve, and the reported configuration sits above the random traffic-splitting baseline. A no-router ablation, always the cheapest fixer with the handoff, ties the routed system on this benchmark, so the handoff rather than the routing decision carries the result. A paired calibration study points to the mechanism: the handoff appears to redistribute rather than add solving ability, lifting the three cheaper fixers while slightly hurting the strongest, though at $N=99$ the per-fixer effects are directional only; the searcher's hidden states improve cost routing on the calibration labels while the handoff's own text does not. The searcher's compute adds less than half a cent of GPU time per task.