SEAICLCVJun 11

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

arXiv:2606.13239v115.3
Predicted impact top 20% in SE · last 90 daysOriginality Highly original
AI Analysis

This work addresses the bottleneck of professional software manipulation for AI agents, offering a novel paradigm that significantly outperforms existing GUI-based approaches in industrial CAD software.

The paper identifies the Component Object Model (COM) as a unified executable abstraction for professional software manipulation, proposing a new paradigm that reframes interaction as deterministic program synthesis. Experiments show that COM-based execution yields substantial gains over GUI-based agents, with the proposed ComActor achieving state-of-the-art performance on the new ComCADBench benchmark.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes