@inproceedings{ma-etal-2026-agent,
title = "{A}gent+{P}: Guiding {UI} Agents via Symbolic Planning",
author = "Ma, Shang and
Xiao, Xusheng and
Ye, Yanfang",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.26/",
pages = "561--578",
ISBN = "979-8-89176-439-2",
abstract = "Large Language Model (LLM)-based UI agents show great promise for UI automation but of- ten hallucinate in long-horizon tasks due to their lack of understanding of the global UI transition structure. To address this, we in- troduce 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 Transi- tion Graph (UTG), which allows us to refor- mulate 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 explo- ration and guiding the agent to achieve the au- tomation 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 im- proves the success rates of state-of-the-art UI agents by up to 14.32{\%} and reduces the ac- tion steps by 37.70{\%}. Our code is available at: https://github.com/KiteFlyKid/agentp."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2026-agent">
<titleInfo>
<title>Agent+P: Guiding UI Agents via Symbolic Planning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shang</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xusheng</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanfang</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Large Language Model (LLM)-based UI agents show great promise for UI automation but of- ten hallucinate in long-horizon tasks due to their lack of understanding of the global UI transition structure. To address this, we in- troduce 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 Transi- tion Graph (UTG), which allows us to refor- mulate 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 explo- ration and guiding the agent to achieve the au- tomation 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 im- proves the success rates of state-of-the-art UI agents by up to 14.32% and reduces the ac- tion steps by 37.70%. Our code is available at: https://github.com/KiteFlyKid/agentp.</abstract>
<identifier type="citekey">ma-etal-2026-agent</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.26/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>561</start>
<end>578</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Agent+P: Guiding UI Agents via Symbolic Planning
%A Ma, Shang
%A Xiao, Xusheng
%A Ye, Yanfang
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F ma-etal-2026-agent
%X Large Language Model (LLM)-based UI agents show great promise for UI automation but of- ten hallucinate in long-horizon tasks due to their lack of understanding of the global UI transition structure. To address this, we in- troduce 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 Transi- tion Graph (UTG), which allows us to refor- mulate 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 explo- ration and guiding the agent to achieve the au- tomation 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 im- proves the success rates of state-of-the-art UI agents by up to 14.32% and reduces the ac- tion steps by 37.70%. Our code is available at: https://github.com/KiteFlyKid/agentp.
%U https://aclanthology.org/2026.aacl-long.26/
%P 561-578
Markdown (Informal)
[Agent+P: Guiding UI Agents via Symbolic Planning](https://aclanthology.org/2026.aacl-long.26/) (Ma et al., AACL-IJCNLP 2026)
ACL
- Shang Ma, Xusheng Xiao, and Yanfang Ye. 2026. Agent+P: Guiding UI Agents via Symbolic Planning. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 561–578, Hengqin, China. Association for Computational Linguistics.