Papers
arxiv:2606.13239

ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm

Published on Jun 11
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,

Abstract

COM-as-Action paradigm enables deterministic program synthesis for professional software interaction, outperforming GUI-based approaches in industrial CAD tasks through self-correcting agent training.

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.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2606.13239
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2606.13239 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2606.13239 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.13239 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.