# Agent+P: Guiding UI Agents via Symbolic Planning

arXiv: https://arxiv.org/abs/2510.06042 · HTML: https://mlsanity.com/paper/2510.06042/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 22 of 22)

- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning](https://mlsanity.com/paper/2305.14909/) (2023)
- [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023)
- [ScreenAI: A Vision-Language Model for UI and Infographics Understanding](https://mlsanity.com/paper/2402.04615/) (2024)
- [PlanGenLLMs: A Modern Survey of LLM Planning Capabilities](https://mlsanity.com/paper/2502.11221/) (2025)
- [Screen2Vec: Semantic Embedding of GUI Screens and GUI Components](https://mlsanity.com/paper/2101.11103/) (2021)
- [Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment](https://mlsanity.com/paper/2503.15937/) (2025)
- [GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation](https://mlsanity.com/paper/2310.00800/) (2023)
- [GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration](https://mlsanity.com/paper/2503.17709/) (2025)
- [Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills](https://mlsanity.com/paper/2506.10387/) (2025)
- [An Empathy-Based Sandbox Approach to Bridge the Privacy Gap among Attitudes, Goals, Knowledge, and Behaviors](https://mlsanity.com/paper/2309.14510/) (2023)
- [LLMs4All: A Review of Large Language Models Across Academic Disciplines](https://mlsanity.com/paper/2509.19580/) (2025)
- [GUI Testing Arena: A Unified Benchmark for Advancing Autonomous GUI Testing Agent](https://mlsanity.com/paper/2412.18426/) (2024)
- [Language Models can Infer Action Semantics for Symbolic Planners from Environment Feedback](https://mlsanity.com/paper/2406.02791/) (2024)
- [ResTest: Targeted Coverage of Residual Not-Covered Code Using Large Language Models for Web GUI Testing](https://mlsanity.com/paper/2506.00520/) (2025)
- [MadDroid: Characterising and Detecting Devious Ad Content for Android Apps](https://mlsanity.com/paper/2002.01656/) (2020)
- [Careful About What App Promotion Ads Recommend! Detecting and Explaining Malware Promotion via App Promotion Graph](https://mlsanity.com/paper/2410.07588/) (2024)

## Built on by (most cited first, 1 of 1)

- [Plover: Steering GUI Agents through Plan-Centric Interaction](https://mlsanity.com/paper/2607.15193/) (2026)

## Abstract (arXiv)

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%.