Agent+P: Guiding UI Agents via Symbolic Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Shang, Xiao, Xusheng, Ye, Yanfang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914239002705920
author Ma, Shang
Xiao, Xusheng
Ye, Yanfang
author_facet Ma, Shang
Xiao, Xusheng
Ye, Yanfang
contents Large Language Model (LLM)-based UI agents show great promise for UI automation but often hallucinate in long-horizon tasks due to their lack of understanding of the global UI transition structure. To address this, we introduce AGENT+P, a novel framework that leverages symbolic planning to guide LLM-based UI agents. Specifically, we model an app's UI transition structure as a UI Transition Graph (UTG), which allows us to reformulate the UI automation task as a pathfinding problem on the UTG. This further enables an off-the-shelf symbolic planner to generate a provably correct and optimal high-level plan, preventing the agent from redundant exploration and guiding the agent to achieve the automation goals. AGENT+P is designed as a plug-and-play framework to enhance existing UI agents. Evaluation on the AndroidWorld benchmark demonstrates that AGENT+P improves the success rates of state-of-the-art UI agents by up to 14.31% and reduces the action steps by 37.70%.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06042
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Agent+P: Guiding UI Agents via Symbolic Planning
Ma, Shang
Xiao, Xusheng
Ye, Yanfang
Multiagent Systems
Large Language Model (LLM)-based UI agents show great promise for UI automation but often hallucinate in long-horizon tasks due to their lack of understanding of the global UI transition structure. To address this, we introduce AGENT+P, a novel framework that leverages symbolic planning to guide LLM-based UI agents. Specifically, we model an app's UI transition structure as a UI Transition Graph (UTG), which allows us to reformulate the UI automation task as a pathfinding problem on the UTG. This further enables an off-the-shelf symbolic planner to generate a provably correct and optimal high-level plan, preventing the agent from redundant exploration and guiding the agent to achieve the automation goals. AGENT+P is designed as a plug-and-play framework to enhance existing UI agents. Evaluation on the AndroidWorld benchmark demonstrates that AGENT+P improves the success rates of state-of-the-art UI agents by up to 14.31% and reduces the action steps by 37.70%.
title Agent+P: Guiding UI Agents via Symbolic Planning
topic Multiagent Systems
url https://arxiv.org/abs/2510.06042