# CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning

arXiv: https://arxiv.org/abs/2603.02951 · HTML: https://mlsanity.com/paper/2603.02951/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 50 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 30 of 42)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [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)
- [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents](https://mlsanity.com/paper/2504.10458/) (2025)
- [ShowUI: One Vision-Language-Action Model for GUI Visual Agent](https://mlsanity.com/paper/2411.17465/) (2024)
- [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://mlsanity.com/paper/2406.11896/) (2024)
- [OmniParser for Pure Vision Based GUI Agent](https://mlsanity.com/paper/2408.00203/) (2024)
- [On the Effects of Data Scale on UI Control Agents](https://mlsanity.com/paper/2406.03679/) (2024)
- [UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning](https://mlsanity.com/paper/2503.21620/) (2025)
- [Learning without Forgetting for Vision-Language Models](https://mlsanity.com/paper/2305.19270/) (2023)
- [GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents](https://mlsanity.com/paper/2505.15810/) (2025)
- [InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection](https://mlsanity.com/paper/2501.04575/) (2025)
- [GUI-G2: Gaussian Reward Modeling for GUI Grounding](https://mlsanity.com/paper/2507.15846/) (2025)
- [Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion](https://mlsanity.com/paper/2407.14143/) (2024)
- [Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training](https://mlsanity.com/paper/2507.05386/) (2025)
- [Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task](https://mlsanity.com/paper/2208.12037/) (2022)
- [Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection](https://mlsanity.com/paper/2307.12427/) (2023)
- [Memorizing Complementation Network for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2208.05610/) (2022)

## Built on by (most cited first, 3 of 3)

- [AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents](https://mlsanity.com/paper/2606.02461/) (2026)
- [Scaling GUI Agents with Visual State Transitions](https://mlsanity.com/paper/2607.24112/) (2026)
- [LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning](https://mlsanity.com/paper/2606.24901/) (2026)

## Abstract (arXiv)

Graphical User Interface (GUI) Agents, benefiting from recent advances in multimodal large language models (MLLM), have achieved significant development. However, due to the frequent updates of GUI applications, adapting to new tasks without forgetting old tasks in GUI continual learning remains an open problem. In this work, we reveal that while Supervised Fine-Tuning (SFT) facilitates fast adaptation, it often triggers knowledge overwriting, whereas Reinforcement Learning (RL) demonstrates an inherent resilience that shields prior interaction logic from erasure. Based on this insight, we propose a Continual GUI Learning (CGL) framework that dynamically balances adaptation efficiency and skill retention by enhancing the synergy between SFT and RL. Specifically, we introduce an SFT proportion adjustment mechanism guided by policy entropy to dynamically control the weight allocation between the SFT and RL training phases. To resolve explicit gradient interference, we further develop a specialized gradient surgery strategy. By projecting exploratory SFT gradients onto GRPO-based anchor gradients, our method explicitly clips the components of SFT gradients that conflict with GRPO. On top of that, we establish an AndroidControl-CL benchmark, which divides GUI applications into distinct task groups to effectively simulate and evaluate the performance of continual GUI learning. Experimental results demonstrate the effectiveness of our proposed CGL framework across continual learning scenarios. The benchmark, code, and model will be made publicly available.