# GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Tasks

arXiv: https://arxiv.org/abs/2509.23738 · HTML: https://mlsanity.com/paper/2509.23738/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Process reward models for reasoning, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 44 of its 44 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 30 of 44)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [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)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (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)
- [Android in the Wild: A Large-Scale Dataset for Android Device Control](https://mlsanity.com/paper/2307.10088/) (2023)
- [Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction](https://mlsanity.com/paper/2412.04454/) (2024)
- [GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents](https://mlsanity.com/paper/2504.10458/) (2025)
- [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://mlsanity.com/paper/2406.11896/) (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)
- [UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning](https://mlsanity.com/paper/2503.21620/) (2025)
- [OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis](https://mlsanity.com/paper/2412.19723/) (2024)

## Built on by (most cited first, 26 of 26)

- [A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models](https://mlsanity.com/paper/2510.08049/) (2025)
- [Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning](https://mlsanity.com/paper/2601.03872/) (2026)
- [A Survey of Inductive Reasoning for Large Language Models](https://mlsanity.com/paper/2510.10182/) (2025)
- [MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism](https://mlsanity.com/paper/2606.07512/) (2026)
- [StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure](https://mlsanity.com/paper/2607.11388/) (2026)
- [Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions](https://mlsanity.com/paper/2604.07277/) (2026)
- [SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context](https://mlsanity.com/paper/2604.11716/) (2026)
- [EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training](https://mlsanity.com/paper/2604.19485/) (2026)
- [Video-Based Reward Modeling for Computer-Use Agents](https://mlsanity.com/paper/2603.10178/) (2026)
- [StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents](https://mlsanity.com/paper/2606.07027/) (2026)
- [OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models](https://mlsanity.com/paper/2607.28609/) (2026)
- [GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments](https://mlsanity.com/paper/2609.00048/) (2026)
- [A History-Aware Visually Grounded Critic for Computer Use Agents](https://mlsanity.com/paper/2606.11078/) (2026)
- [ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks](https://mlsanity.com/paper/2606.21654/) (2026)
- [Teach it to stop, not just to click](https://mlsanity.com/paper/2607.17136/) (2026)
- [Software Engineering for and with GUI Agent](https://mlsanity.com/paper/2608.09278/) (2026)
- [Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments](https://mlsanity.com/paper/2608.24099/) (2026)
- [TVWorld: Foundations for Remote-Control TV Agents](https://mlsanity.com/paper/2601.13142/) (2026)
- [Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment](https://mlsanity.com/paper/2605.14311/) (2026)
- [VisCritic: Visual State Comparison as Process Reward for GUI Agents](https://mlsanity.com/paper/2606.24525/) (2026)
- [StepReflect: Structured UI Transition Reflection for Mobile GUI Agents](https://mlsanity.com/paper/2608.05587/) (2026)
- [Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization](https://mlsanity.com/paper/2609.02309/) (2026)
- [Absorbed in Inertia: Activation Analysis for Computer-Use Agents](https://mlsanity.com/paper/2609.37176/) (2026)
- [Consistent Plan-Act for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2609.38891/) (2026)
- [ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents](https://mlsanity.com/paper/2609.40253/) (2026)
- [Adaptive-Group Process Rewards for GUI Agents](https://mlsanity.com/paper/2610.17710/) (2026)

## Abstract (arXiv)

Autonomous agents for long-sequence Graphical User Interface tasks are hindered by sparse rewards and the intractable credit assignment problem. To address these challenges, we introduce GUI-Shepherd, a Process Reward Model that provides dense, step-by-step feedback to guide agents. GUI-Shepherd is trained on a diverse large-scale data set of 52k interactions that features human-annotated scores and GPT-4o generated rationales, enabling it to serve both as a reward provider for RL training and as a verifier for inference. As far as we know, we are the first to conduct a systematic study of process supervision in GUI agents, across diverse settings from online long-horizon tasks to offline single-step prediction. On the online AndroidWorld benchmark, GUI-Shepherd improves success rate by 7.7 points via multi-turn online PPO, significantly outperforming Outcome Reward Model based competitors. When used as an inference verifier, it brings 5.1 points improvements. The benefits generalize to the offline AndroidControl benchmark, with gains of 2.2 points as a reward provider and 4.3 points as a verifier. Collectively, our results establish that high-fidelity process supervision is critical for building more capable GUI agents and present a generalizable solution.