# Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study

arXiv: https://arxiv.org/abs/2503.16788 · HTML: https://mlsanity.com/paper/2503.16788/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 27 of its 56 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 27 of 27)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://mlsanity.com/paper/2401.10935/) (2024)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Android in the Wild: A Large-Scale Dataset for Android Device Control](https://mlsanity.com/paper/2307.10088/) (2023)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale](https://mlsanity.com/paper/2409.08264/) (2024)
- [On the Effects of Data Scale on UI Control Agents](https://mlsanity.com/paper/2406.03679/) (2024)
- [GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices](https://mlsanity.com/paper/2406.08451/) (2024)
- [You Only Look at Screens: Multimodal Chain-of-Action Agents](https://mlsanity.com/paper/2309.11436/) (2023)
- [AutoDroid: LLM-powered Task Automation in Android](https://mlsanity.com/paper/2308.15272/) (2023)
- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [Android in the Zoo: Chain-of-Action-Thought for GUI Agents](https://mlsanity.com/paper/2403.02713/) (2024)
- [Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning](https://mlsanity.com/paper/2401.06805/) (2024)
- [Small Language Models: Survey, Measurements, and Insights](https://mlsanity.com/paper/2409.15790/) (2024)
- [AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents](https://mlsanity.com/paper/2410.24024/) (2024)
- [META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI](https://mlsanity.com/paper/2205.11029/) (2022)
- [Enabling Conversational Interaction with Mobile UI using Large Language Models](https://mlsanity.com/paper/2209.08655/) (2022)
- [Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents](https://mlsanity.com/paper/2407.00993/) (2024)
- [LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation](https://mlsanity.com/paper/2404.16054/) (2024)
- [AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation](https://mlsanity.com/paper/2412.18116/) (2024)
- [API Agents vs. GUI Agents: Divergence and Convergence](https://mlsanity.com/paper/2503.11069/) (2025)
- [Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models](https://mlsanity.com/paper/2410.01782/) (2024)
- [Every Software as an Agent: Blueprint and Case Study](https://mlsanity.com/paper/2502.04747/) (2025)

## Built on by (most cited first, 11 of 11)

- [GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents](https://mlsanity.com/paper/2505.15810/) (2025)
- [GUI-Shift: Enhancing VLM-Based GUI Agents through Self-supervised Reinforcement Learning](https://mlsanity.com/paper/2505.12493/) (2025)
- [How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1](https://mlsanity.com/paper/2602.19526/) (2026)
- [SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control](https://mlsanity.com/paper/2508.20018/) (2025)
- [Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents](https://mlsanity.com/paper/2510.02204/) (2025)
- [Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations](https://mlsanity.com/paper/2510.00496/) (2025)
- [BAMI: Training-Free Bias Mitigation in GUI Grounding](https://mlsanity.com/paper/2605.06664/) (2026)
- [Faithful Mobile GUI Agents with Guided Advantage Estimator](https://mlsanity.com/paper/2605.01208/) (2026)
- [Software Engineering for and with GUI Agent](https://mlsanity.com/paper/2608.09278/) (2026)
- [TVWorld: Foundations for Remote-Control TV Agents](https://mlsanity.com/paper/2601.13142/) (2026)
- [Thinking Is Not Telling: Information Disclosure in User-Service LLM Agents](https://mlsanity.com/paper/2602.07796/) (2026)

## Abstract (arXiv)

Reasoning capabilities have significantly improved the performance of vision-language models (VLMs) in domains such as mathematical problem-solving, coding, and visual question-answering. However, their impact on real-world applications remains unclear. This paper presents the first empirical study on the effectiveness of reasoning-enabled VLMs in mobile GUI agents, a domain that requires interpreting complex screen layouts, understanding user instructions, and executing multi-turn interactions. We evaluate two pairs of commercial models--Gemini 2.0 Flash and Claude 3.7 Sonnet--comparing their base and reasoning-enhanced versions across two static benchmarks (ScreenSpot and AndroidControl) and one interactive environment (AndroidWorld). We surprisingly find the Claude 3.7 Sonnet reasoning model achieves state-of-the-art performance on AndroidWorld. However, reasoning VLMs generally offer marginal improvements over non-reasoning models on static benchmarks and even degrade performance in some agent setups. Notably, reasoning and non-reasoning VLMs fail on different sets of tasks, suggesting that reasoning does have an impact, but its benefits and drawbacks counterbalance each other. We attribute these inconsistencies to the limitations of benchmarks and VLMs. Based on the findings, we provide insights for further enhancing mobile GUI agents in terms of benchmarks, VLMs, and their adaptability in dynamically invoking reasoning VLMs. The experimental data are publicly available at https://github.com/LlamaTouch/VLM-Reasoning-Traces.