# ProgRM: Build Better GUI Agents with Progress Rewards

arXiv: https://arxiv.org/abs/2505.18121 · HTML: https://mlsanity.com/paper/2505.18121/

## Key facts

- Cited by 21 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 36 of its 41 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)
- 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 36)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://mlsanity.com/paper/2501.07301/) (2025)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception](https://mlsanity.com/paper/2401.16158/) (2024)
- [Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction](https://mlsanity.com/paper/2412.04454/) (2024)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning](https://mlsanity.com/paper/2411.02337/) (2024)
- [GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents](https://mlsanity.com/paper/2504.10458/) (2025)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://mlsanity.com/paper/2406.11896/) (2024)
- [Free Process Rewards without Process Labels](https://mlsanity.com/paper/2412.01981/) (2024)
- [OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis](https://mlsanity.com/paper/2412.19723/) (2024)
- [UFO: A UI-Focused Agent for Windows OS Interaction](https://mlsanity.com/paper/2402.07939/) (2024)
- [Autonomous Evaluation and Refinement of Digital Agents](https://mlsanity.com/paper/2404.06474/) (2024)
- [AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials](https://mlsanity.com/paper/2412.09605/) (2024)
- [Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.07572/) (2025)
- [Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments](https://mlsanity.com/paper/2501.10893/) (2025)
- [Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents](https://mlsanity.com/paper/2502.11357/) (2025)
- [DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents](https://mlsanity.com/paper/2410.14803/) (2024)
- [SteP: Stacked LLM Policies for Web Actions](https://mlsanity.com/paper/2310.03720/) (2023)
- [Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents](https://mlsanity.com/paper/2412.13194/) (2024)
- [Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale](https://mlsanity.com/paper/2409.15637/) (2024)
- [Large Language Models Are Semi-Parametric Reinforcement Learning Agents](https://mlsanity.com/paper/2306.07929/) (2023)

## Built on by (most cited first, 21 of 21)

- [A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models](https://mlsanity.com/paper/2510.08049/) (2025)
- [WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance](https://mlsanity.com/paper/2511.12997/) (2025)
- [HiconAgent: History Context-aware Policy Optimization for GUI Agents](https://mlsanity.com/paper/2512.01763/) (2025)
- [Geoint-R1: Formalizing Multimodal Geometric Reasoning with Dynamic Auxiliary Constructions](https://mlsanity.com/paper/2508.03173/) (2025)
- [Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding](https://mlsanity.com/paper/2606.00564/) (2026)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [PACR: Progressively Ascending Confidence Reward for LLM Reasoning](https://mlsanity.com/paper/2510.22255/) (2025)
- [Retrospective Progress-Aware Self-Refinement for LLM Agent Training](https://mlsanity.com/paper/2606.14302/) (2026)
- [UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics](https://mlsanity.com/paper/2604.02345/) (2026)
- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [Video-Based Reward Modeling for Computer-Use Agents](https://mlsanity.com/paper/2603.10178/) (2026)
- [GUI Agents with Reinforcement Learning: Toward Digital Inhabitants](https://mlsanity.com/paper/2604.27955/) (2026)
- [StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents](https://mlsanity.com/paper/2606.07027/) (2026)
- [Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization](https://mlsanity.com/paper/2602.13653/) (2026)
- [UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations](https://mlsanity.com/paper/2608.15930/) (2026)
- [TVWorld: Foundations for Remote-Control TV Agents](https://mlsanity.com/paper/2601.13142/) (2026)
- [Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability](https://mlsanity.com/paper/2605.07110/) (2026)
- [Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agents](https://mlsanity.com/paper/2608.27866/) (2026)
- [Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents](https://mlsanity.com/paper/2609.27307/) (2026)
- [Absorbed in Inertia: Activation Analysis for Computer-Use Agents](https://mlsanity.com/paper/2609.37176/) (2026)
- [World Potential Model: Pretrained World Knowledge as Progress Potentials](https://mlsanity.com/paper/2610.09560/) (2026)

## Abstract (arXiv)

LLM-based (Large Language Model) GUI (Graphical User Interface) agents can potentially reshape our daily lives significantly. However, current LLM-based GUI agents suffer from the scarcity of high-quality training data owing to the difficulties of trajectory collection and reward annotation. Existing works have been exploring LLMs to collect trajectories for imitation learning or to offer reward signals for online RL training. However, the Outcome Reward Model (ORM) used in existing works cannot provide finegrained feedback and can over-penalize the valuable steps in finally failed trajectories. To this end, we propose Progress Reward Model (ProgRM) to provide dense informative intermediate rewards by predicting a task completion progress for each step in online training. To handle the challenge of progress reward label annotation, we further design an efficient LCS-based (Longest Common Subsequence) self-annotation algorithm to discover the key steps in trajectories and assign progress labels accordingly. ProgRM is evaluated with extensive experiments and analyses. Actors trained with ProgRM outperform leading proprietary LLMs and ORM-trained actors, illustrating the effectiveness of ProgRM. The codes for experiments will be made publicly available upon acceptance.