arXiv cs.AI· Jingxuan Wei, Jiahao Fu, Fuqiang Wang, Xiaoming Wu, Yuwen Liu, Kaiwen Wei, Ming Yang, Junnan Zhu·· 10 小时前AI 评分26
MAGAR：面向 GUI 三维机械装配与最小返工的多模态智能体框架
MAGAR: Multimodal Agents for GUI-Based 3D Mechanical Assembly and Minimal Rework
AI 导读
MAGAR 是一个基于冻结策略的选择性纠错框架，通过将纠错粒度与输出依赖匹配，在 MAGAR-Bench 留出装配族状态上把任务均衡总分 Overall 从 37.50 提升到 41.39，三项任务均有增益。
正文 · 原文
Abstract:A GUI command can be correct at the interface level yet still produce an incorrect assembly. An agent must identify the relevant components, respect their structural relationships, and determine which parts should move during recovery. We introduce MAGAR-Bench, a benchmark of 4,000 multimodal samples from 26 assembly families that separates Assembly Decision, Atomic Action, and Minimal Rework. For rework, the objective counts distinct moved parts within the validated recovery candidate set for each state, rather than the number of actions. We also introduce MAGAR, a selective correction framework built on a frozen policy obtained by supervised fine-tuning. Its key design matches correction granularity to output dependencies. Structured candidates revise assembly fields and rework scope, while complete action candidates keep native GUI primitives coupled with their parameters. A learned selector retains the original prediction unless a candidate passes a task-specific intervention threshold. On recorded states from held-out assembly families, MAGAR improves Overall, the task-balanced aggregate, from 37.50 to 41.39, with gains on all three tasks. Across 209 interventions, 70 correct an error and 22 introduce one. These results support task-specific correction while highlighting the remaining tradeoff between fixing errors and preserving reliable predictions.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.02472 [cs.AI] |
| (or arXiv:2611.02472v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.02472 arXiv-issued DOI via DataCite |
Submission history
From: Jiahao Fu [view email]
[v1]
Mon, 2 Nov 2026 03:40:49 UTC (5,051 KB)
[v2]
Tue, 10 Nov 2026 09:01:56 UTC (5,058 KB)
来源：arXiv cs.AI · arxiv.org