GPA: Learning GUI Process Automation from Demonstrations

TL;DR

GPA is a vision-based GUI automation method that offers robustness, reliability, and privacy, enabling fast, stable process replay from a single demonstration, outperforming existing solutions in success rate and speed.

Contribution

GPA introduces a novel approach combining Monte Carlo localization and readiness calibration for robust, deterministic, and private GUI process automation from demonstrations.

Findings

GPA achieves higher success rate than Gemini 3 Pro in long-horizon tasks.

GPA is 10 times faster in executing GUI tasks.

GPA enables fast, reliable, and privacy-preserving GUI automation.

Abstract

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.