TLDR
Terminal Agent 正日益超越软件工程，部署到科学及其他专业领域。构建训练环境需要可执行参考行为与领域特定的验证器，以区分语义正确性与表面似是而非的产物。为每个任务编写这些组件需要反复工程投入，限制了复用性。本文提出 software-in-the-loop reconstruction，一种自监督框架，从现有软件工作流中获取参考输出与验证目标，即可将结构化输入映射为Terminal agents are increasingly deployed beyond software engineering in science and other specialized domains. Constructing training environments requires executable reference behavior and a domain-specific verifier that distinguishes semantic correctness from superficially plausible artifacts. Authoring these components for each task requires repeated engineering and limits reuse. We introduce software-in-the-loop reconstruction, a self-supervised framework that obtains reference outputs and verification targets from existing software workflows, executable programs mapping structured inputs