Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accumulation, while API-basedapproaches struggle with heterogeneous protocols and inaccessible commercial interfaces. In this work,we identify the Component Object Model (COM) as a unified executable abstraction, proposing COM-as-Action: a new paradigm that reframes professional software interaction as deterministic program synthesisrather than sequential visual control. To validate this paradigm in the most demanding environments, weintroduce ComCADBench, the first benchmark for agents operating real industrial CAD software. Ourexperiments reveal a substantial paradigm gap: frontier proprietary models achieve near-zero successunder GUI-based interaction, whereas COM-based execution yields substantial immediate gains. Tobridge the remaining gap between syntactic correctness and geometric accuracy, we develop ComActor, aself-correcting agent trained through a progressive three-stage framework, alongside ComForge, a scalableplatform for large-scale training in Windows containers. Extensive experiments show that ComActorachieves state-of-the-art performance on ComCADBench, with strong resilience in long-horizon taskswhere baselines collapse, and generalizes to external CAD benchmark.

翻译：现有计算机操控代理在专业软件操作中仍存在根本性局限：基于图形用户界面的代理面临脆弱的视觉定位与长程错误累积问题，而基于应用编程接口的方法则受困于异构协议与不可访问的商业接口。本研究将组件对象模型（COM）识别为统一的可执行抽象，提出"COM即动作"新范式——将专业软件交互重构为确定性程序合成，而非序列化视觉控制。为在最具挑战性的环境中验证该范式，我们提出ComCADBench——首个面向真实工业CAD软件操作代理的基准测试。实验揭示显著的范式鸿沟：前沿商业模型在基于GUI的交互中成功率近乎为零，而基于COM的执行方法则能取得立竿见影的性能提升。为弥合句法正确性与几何精确性之间的剩余差距，我们开发了ComActor——通过渐进式三阶段框架训练的自纠正代理，同时构建ComForge——支持Windows容器大规模训练的可扩展平台。大量实验表明，ComActor在ComCADBench上取得最优性能，在基线方法崩溃的长程任务中展现出强鲁棒性，并可泛化至外部CAD基准测试。