FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Bobo, Wang, Yuheng, Fei, Hao, Li, Juncheng, Ji, Wei, Lee, Mong-Li, Hsu, Wynne
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908389593841664
author Li, Bobo
Wang, Yuheng
Fei, Hao
Li, Juncheng
Ji, Wei
Lee, Mong-Li
Hsu, Wynne
author_facet Li, Bobo
Wang, Yuheng
Fei, Hao
Li, Juncheng
Ji, Wei
Lee, Mong-Li
Hsu, Wynne
contents Online form filling is a common yet labor-intensive task involving extensive keyboard and mouse interactions. Despite the long-standing vision of automating this process with "one click", existing tools remain largely rule-based and lack generalizable, generative capabilities. Recent advances in Multimodal Large Language Models (MLLMs) have enabled promising agents for GUI-related tasks in general-purpose scenarios. However, they struggle with the unique challenges of form filling, such as flexible layouts and the difficulty of aligning textual instructions with on-screen fields. To bridge this gap, we formally define the form-filling task and propose FormFactory, an interactive benchmarking suite comprising a web-based interface, backend evaluation module, and carefully constructed dataset. Our benchmark covers diverse real-world scenarios, incorporates various field formats, and simulates high-fidelity form interactions. We conduct a comprehensive evaluation of state-of-the-art MLLMs and observe that no model surpasses 5% accuracy, underscoring the inherent difficulty of the task. These findings also reveal significant limitations in current models' visual layout reasoning and field-value alignment abilities. We hope our benchmark can serve as a stepping stone for further research into robust, practical form-filling agents.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01520
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents
Li, Bobo
Wang, Yuheng
Fei, Hao
Li, Juncheng
Ji, Wei
Lee, Mong-Li
Hsu, Wynne
Computation and Language
Online form filling is a common yet labor-intensive task involving extensive keyboard and mouse interactions. Despite the long-standing vision of automating this process with "one click", existing tools remain largely rule-based and lack generalizable, generative capabilities. Recent advances in Multimodal Large Language Models (MLLMs) have enabled promising agents for GUI-related tasks in general-purpose scenarios. However, they struggle with the unique challenges of form filling, such as flexible layouts and the difficulty of aligning textual instructions with on-screen fields. To bridge this gap, we formally define the form-filling task and propose FormFactory, an interactive benchmarking suite comprising a web-based interface, backend evaluation module, and carefully constructed dataset. Our benchmark covers diverse real-world scenarios, incorporates various field formats, and simulates high-fidelity form interactions. We conduct a comprehensive evaluation of state-of-the-art MLLMs and observe that no model surpasses 5% accuracy, underscoring the inherent difficulty of the task. These findings also reveal significant limitations in current models' visual layout reasoning and field-value alignment abilities. We hope our benchmark can serve as a stepping stone for further research into robust, practical form-filling agents.
title FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents
topic Computation and Language
url https://arxiv.org/abs/2506.01520