paper-with-me

홈 › Papers

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

2026-06-11 · Jiaxin Ai, Tao Hu, Xuemeng Yang, Shu Zou, Hairong Zhang, Daocheng Fu, Yu Yang, Hongbin Zhou, Nianchen Deng, Pinlong Cai, Zhongyuan Wang, Botian Shi, Kaipeng Zhang, Licheng Wen arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.13239

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Grounding

Similar Papers 제목 키워드 기반

Identifying Human Edited Images using a CNN

2021-01-09 · Jordan Lee, Willy Lin, Konstantinos Ntalis, Anirudh Shah 외

Most non-professional photo manipulations are not made using propriety software like Adobe Photoshop, which is expensive and complicated to use for the average consumer selfie-taker or meme-maker. Instead, these individu…

Reframe Anything: LLM Agent for Open World Video Reframing

2024-03-10 · Jiawang Cao, Yongliang Wu, Weiheng Chi, Wenbo Zhu 외

The proliferation of mobile devices and social media has revolutionized content dissemination, with short-form video becoming increasingly prevalent. This shift has introduced the challenge of video reframing to fit vari…

object-detectionObject DetectionSalient Object DetectionVideo Editing+1

New Interaction Paradigm for Complex EDA Software Leveraging GPT

2023-07-27 · Boyu Han, Xinyu Wang, Yifan Wang, Junyu Yan 외

In the rapidly growing field of electronic design automation (EDA), professional software such as KiCad, Cadence , and Altium Designer provide increasingly extensive design functionalities. However, the intricate command…

Task Planning

The Perspective of Software Professionals on Algorithmic Racism

2023-06-27 · Ronnie de Souza Santos, Luiz Fernando de Lima, Cleyton Magalhaes

Context. Algorithmic racism is the term used to describe the behavior of technological solutions that constrains users based on their ethnicity. Lately, various data-driven software systems have been reported to discrimi…

Descriptive

ProSoftArena: Benchmarking Hierarchical Capabilities of Multimodal Agents in Professional Software Environments

2025-12-30 · Jiaxin Ai, Yukang Feng, Fanrui Zhang, Jianwen Sun 외 arxiv

Multimodal agents are making rapid progress on general computer-use tasks, yet existing benchmarks remain largely confined to browsers and basic desktop applications, falling short in professional software workflows that…