Saved in:
Bibliographic Details
Main Authors: Zhao, Zirui, Liew, Jun Hao, Yang, Yan, Yang, Wenzhuo, Luo, Ziyang, Sahoo, Doyen, Savarese, Silvio, Li, Junnan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.01676
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915914873569280
author Zhao, Zirui
Liew, Jun Hao
Yang, Yan
Yang, Wenzhuo
Luo, Ziyang
Sahoo, Doyen
Savarese, Silvio
Li, Junnan
author_facet Zhao, Zirui
Liew, Jun Hao
Yang, Yan
Yang, Wenzhuo
Luo, Ziyang
Sahoo, Doyen
Savarese, Silvio
Li, Junnan
contents GUI Process Automation (GPA) is a lightweight but general vision-based Robotic Process Automation (RPA), which enables fast and stable process replay with only a single demo. Addressing the fragility of traditional RPA and the non-deterministic risks of current vision language model-based GUI agents, GPA introduces three core benefits: (1) Robustness via Sequential Monte Carlo-based localization to handle rescaling and detection uncertainty; (2) Deterministic and Reliability safeguarded by readiness calibration; and (3) Privacy through fast, fully local execution. This approach delivers the adaptability, robustness, and security required for enterprise workflows. It can also be used as an MCP/CLI tool by other agents with coding capabilities so that the agent only reasons and orchestrates while GPA handles the GUI execution. We conducted a pilot experiment to compare GPA with Gemini 3 Pro (with CUA tools) and found that GPA achieves higher success rate with 10 times faster execution speed in finishing long-horizon GUI tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_01676
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GPA: Learning GUI Process Automation from Demonstrations
Zhao, Zirui
Liew, Jun Hao
Yang, Yan
Yang, Wenzhuo
Luo, Ziyang
Sahoo, Doyen
Savarese, Silvio
Li, Junnan
Computer Vision and Pattern Recognition
Artificial Intelligence
Software Engineering
GUI Process Automation (GPA) is a lightweight but general vision-based Robotic Process Automation (RPA), which enables fast and stable process replay with only a single demo. Addressing the fragility of traditional RPA and the non-deterministic risks of current vision language model-based GUI agents, GPA introduces three core benefits: (1) Robustness via Sequential Monte Carlo-based localization to handle rescaling and detection uncertainty; (2) Deterministic and Reliability safeguarded by readiness calibration; and (3) Privacy through fast, fully local execution. This approach delivers the adaptability, robustness, and security required for enterprise workflows. It can also be used as an MCP/CLI tool by other agents with coding capabilities so that the agent only reasons and orchestrates while GPA handles the GUI execution. We conducted a pilot experiment to compare GPA with Gemini 3 Pro (with CUA tools) and found that GPA achieves higher success rate with 10 times faster execution speed in finishing long-horizon GUI tasks.
title GPA: Learning GUI Process Automation from Demonstrations
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2604.01676