CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks

2025-08-15 · Songqin Nong, Xiaoxuan Tang, Jingxuan Xu, Sheng Zhou, Jianfeng Chen, Tao Jiang, Wenhao Xu arxiv

As autonomous agents become adept at understanding and interacting with graphical user interface (GUI) environments, a new era of automated task execution is emerging. Recent studies have demonstrated that Reinforcement Learning (RL) can effectively enhance agents' performance in dynamic interactive GUI environments. However, these methods face two key limitations: (1) they overlook the significant variation in difficulty across different GUI tasks by treating the entire training data as a uniform set, which hampers the agent's ability to adapt its learning process; and (2) most approaches collapse task-specific nuances into a single, coarse reward, leaving the agent with a uniform signal that yields inefficient policy updates. To address these limitations, we propose CRAFT-GUI, a curriculum learning framework based on Group Relative Policy Optimization (GRPO) that explicitly accounts for the varying difficulty across trajectories. To enable more fine-grained policy optimization, we design a reward function that combines simple rule-based signals with model-judged evaluation, providing richer and more nuanced feedback during training. Experimental results demonstrate that our method achieves significant improvements over previous state-of-the-art approaches, outperforming them by 5.6% on public benchmarks Android Control and 10.3% on our internal online benchmarks, respectively. These findings empirically validate the effectiveness of integrating reinforcement learning with curriculum learning in GUI interaction tasks.

📄 PDF Abstract BibTeX arXiv:2508.11360

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft

2021-06-28 · Ingmar Kanitscheider, Joost Huizinga, David Farhi, William Hebgen Guss 외

An important challenge in reinforcement learning is training agents that can solve a wide variety of tasks. If tasks depend on each other (e.g. needing to learn to walk before learning to run), curriculum learning can sp…

Minecraft reinforcement-learning Reinforcement Learning (RL)

Learning to Guide Multiple Heterogeneous Actors from a Single Human Demonstration via Automatic Curriculum Learning in StarCraft II

2022-05-11 · Nicholas Waytowich, James Hare, Vinicius G. Goecks, Mark Mittrick 외

Traditionally, learning from human demonstrations via direct behavior cloning can lead to high-performance policies given that the algorithm has access to large amounts of high-quality data covering the most likely scena…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+2

Maneuver Decision-Making Through Automatic Curriculum Reinforcement Learning Without Handcrafted Reward functions

2023-07-12 · Zhang Hong-Peng

Maneuver decision-making is the core of unmanned combat aerial vehicle for autonomous air combat. To solve this problem, we propose an automatic curriculum reinforcement learning method, which enables agents to learn eff…

Decision Making reinforcement-learning Reinforcement Learning

Growing Action Spaces

2019-06-28 · ICML 2020 1 · Gregory Farquhar, Laura Gustafson, Zeming Lin, Shimon Whiteson 외

In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress. In this work, we use a curriculum of progressively growing action…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Starcraft

Teacher-Student Curriculum Learning

2017-07-01 · Tambet Matiisen, Avital Oliver, Taco Cohen, John Schulman

We propose Teacher-Student Curriculum Learning (TSCL), a framework for automatic curriculum learning, where the Student tries to learn a complex task and the Teacher automatically chooses subtasks from a given set for th…

Minecraft