用COM接口统一操控专业软件，让自动化更稳定高效。
ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm
- 将软件操作转为确定性代码生成，避开视觉识别缺陷。
- 在工业级CAD测试中，新方法成功率远超传统方案。
- 适合需要长期稳定操作的工程自动化场景。
现有计算机使用智能体在专业软件操作上仍存根本局限：基于GUI的智能体依赖脆弱的视觉定位，易产生长序列误差累积；而基于API的方法则面临协议异构与商业接口不可访问问题。本文识别出组件对象模型（COM）作为统一可执行抽象，提出COM-as-Action范式，将专业软件交互重构为确定性程序合成，而非顺序视觉控制。为验证该范式在最严苛环境下的表现，我们引入ComCADBench——首个面向真实工业级CAD软件的智能体基准测试。实验揭示显著范式差距：前沿专有模型在基于GUI的交互下成功率接近零，而基于COM的执行则实现显著即时提升。为弥合语法正确性与几何准确性之间的差距，我们开发了ComActor，一种通过渐进三阶段框架训练的自校正智能体，以及ComForge，一个基于Windows容器的大规模训练可扩展平台。大量实验表明，ComActor在ComCADBench上达到当前最佳性能，在长时序任务中表现出强鲁棒性，并能泛化至外部CAD基准。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。