DCAS：解耦CLI智能体脚手架以跨脚手架内化规划能力

摘要

基于命令行界面(CLI)的软件工程智能体已迅速成熟,然而开放生态系统却收敛到了单一训练环境:用于微调开源模型的轨迹数据集几乎完全是在OpenHands下收集的。基于这些数据微调的模型在OpenHands下表现良好,但在任何非训练脚手架下部署时性能均显著退化。未训练的基座模型并不表现出这种差异,表明该差距由微调引起,且与训练脚手架的约定相关联。我们认为,一个起承重作用的脚手架特有行为是规划结构,这体现在本文所区分的两个层面上:显式规划,即作为一等产物生成的执行前规划;以及隐式规划,即在整个智能体循环中塑造执行过程的结构性约定。基于这一假设,弥合差距需要将规划从固定的脚手架产物转变为模型习得的能力。我们提出解耦CLI智能体脚手架(DCAS)——一种后端替换拦截层,可在不修改脚手架的前提下,在任意CLI脚手架与任意后端模型之间路由API流量,从而实现跨脚手架评估与规划感知的轨迹收集。借助DCAS,一项受控的规划来源干预证实规划质量是一个高杠杆组件,其取得的收益超过我们所观察到的跨脚手架性能下降。在单一脚手架下,基于少量DCAS收集的规划感知轨迹微调的模型,在非训练脚手架上均取得一致性提升;并且,上述两种层面的规划在训练数据中可经验性地加以区分。

English

CLI-based software-engineering agents have matured rapidly, yet the open ecosystem has converged on a single training environment: trajectory datasets used to fine-tune open models are collected almost exclusively under OpenHands. Models fine-tuned on this data score well under OpenHands but degrade substantially when deployed under any non-training scaffold. Untrained base models do not show this divergence, indicating the gap is fine-tuning-induced and tied to the conventions of the training scaffold. We argue that a load-bearing scaffold-specific behavior is planning structure, in two senses this paper distinguishes: explicit planning, a pre-execution plan produced as a first-class artifact, and implicit planning, the structural conventions that shape execution throughout the agent loop. Under this hypothesis, closing the gap requires moving planning from a fixed scaffold artifact to a learned model capability. We introduce Decoupling CLI Agent Scaffolding (DCAS), a backend-substitution interception layer that routes API traffic between any CLI scaffold and any backend model without modifying the scaffold, enabling cross-scaffold evaluation and planning-aware trajectory collection. Using DCAS, a controlled plan-source intervention confirms planning quality is a high-leverage component, with gains exceeding the cross-scaffold drops we observe. A model fine-tuned on a small set of DCAS-collected planning-aware trajectories under a single scaffold gains consistently across non-training scaffolds, and the two senses of planning are empirically separable in training data.