Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification

• URL: http://arxiv.org/abs/2607.25904v2
• Date: Wed, 29 Jul 2026 05:13:57 GMT
• Title: Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification
• Abstract summary: We propose an interactive reward agent (IRA) based on a propose-then-verify framework to acquire and verify evidence from the post-execution environment.<n>IRA achieves 86.9% accuracy on GUI-RewardBench, outperforming existing baseline evaluators.
• Score: 26.725458847440507
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graphical user interface task evaluation aims to determine whether a GUI agent has successfully completed a user instruction. Automated GUI task evaluation has received increasing attention because the evaluation results can serve as reward signals for both test-time scaling and post-training. However, reliable GUI task evaluation remains challenging because the judgments often require access to environment states, such as system configurations, file data, and application settings, beyond the screenshots of execution trajectories. In this paper, we propose an interactive reward agent (IRA) based on a propose-then-verify framework to acquire and verify evidence from the post-execution environment. Given a task instruction and a GUI environment after the GUI agent execution, IRA first proposes the task completion conditions and then verifies them by invoking system tools, application tools, and GUI tools. This design combines evidence from both visible interfaces and the environment state in an interactive process. We further introduce GUI-RewardBench, a benchmark of 321 GUI task trajectories spanning 10 Ubuntu desktop application categories. Experiments show that IRA achieves 86.9% accuracy on GUI-RewardBench, outperforming existing evaluator baselines. We further apply IRA to reinforcement learning of GUI agents, achieving a 34.0% OSWorld success rate, which demonstrates that IRA can provide effective reward signals for training GUI agents.

Related papers

• JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition [51.15720718264743]
  We introduce JarvisGUI, a dynamic benchmark that evaluates GUI agents on cross-device requiring coordinated interaction across platforms.<n>JarvisGUI formulates GUI tasks as input-output transformations under a lightweight type system, which allows us to automatically compose multi-step, cross-device transformations.<n>We show that state-of-the-art open-source GUI agents struggle with the state-transfer awareness, cross-platform contextual reasoning, and long-horizon dependency management required for real-world usage.
  arXiv  Detail & Related papers  (2026-09-09T16:59:59Z)
• UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization [70.85564601986263]
  Experimental results show that UI-Copilot-7B achieves state-of-the-art performance on challenging MemGUI-Bench.<n> UI-Copilot-7B delivers a 17.1% absolute improvement on AndroidWorld over the base Qwen model.
  arXiv  Detail & Related papers  (2026-04-15T12:55:46Z)
• GUI-Eyes: Tool-Augmented Perception for Visual Grounding in GUI Agents [39.807839972627015]
  We present GUI-Eyes, a reinforcement learning framework for active visual perception in GUI tasks.<n>We introduce a progressive perception strategy that decomposes decision-making into coarse exploration and fine-grained grounding.<n>On the ScreenSpot-Pro benchmark, GUI-Eyes-3B achieves 44.8% grounding accuracy using only 3k labeled samples.
  arXiv  Detail & Related papers  (2026-01-14T14:27:28Z)
• ProBench: Benchmarking GUI Agents with Accurate Process Information [15.519853892615272]
  We introduce ProBench, a comprehensive benchmark with over 200 challenging GUI tasks covering widely-used scenarios.<n>We extend our dataset to include Process-related Task and design a specialized evaluation method.<n>Our evaluation of advanced GUI agents reveals significant limitations for real-world GUI scenarios.
  arXiv  Detail & Related papers  (2025-11-12T09:49:31Z)
• MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents [88.35544552383581]
  We introduce MMBench-GUI, a hierarchical benchmark for evaluating GUI automation agents across Windows, Linux, iOS, Android, and Web platforms.<n>It comprises four levels: GUI Content Understanding, Element Grounding, Task Automation, and Task Collaboration, covering essential skills for GUI agents.
  arXiv  Detail & Related papers  (2025-07-25T17:59:26Z)
• GTA1: GUI Test-time Scaling Agent [97.58177633084915]
  Graphical user interface (GUI) agents autonomously complete tasks across platforms (eg, Linux) by sequentially decomposing user instructions into action proposals.<n>This paper investigates the aforementioned challenges with our textbfGUI textbfTest-time Scaling textbfAgent, namely GTA1.
  arXiv  Detail & Related papers  (2025-07-08T08:52:18Z)
• MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment [63.62778707277929]
  MobileGUI-RL is a scalable framework that trains GUI agent in online environment.<n>It synthesizes a curriculum of learnable tasks through self-exploration and filtering.<n>It adapts GRPO to GUI navigation with trajectory-aware advantages and composite rewards.
  arXiv  Detail & Related papers  (2025-07-08T07:07:53Z)
• ScaleTrack: Scaling and back-tracking Automated GUI Agents [11.046190201201348]
  We propose ScaleTrack, a training framework by scaling grounding and backtracking planning for automated GUI agents.<n>We collect GUI samples of different synthesis criterions from a wide range of sources, and unified them into the same template for training GUI grounding models.<n>We design a novel training strategy that predicts the next action from the current GUI image, while also backtracking the historical actions that led to the GUI image.
  arXiv  Detail & Related papers  (2025-05-01T09:27:13Z)
• WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting Point [17.165899818213475]
  We introduce WorldGUI, a comprehensive GUI benchmark containing tasks across ten widely used desktop and web applications.<n>WorldGUI-Agent is a universal framework that unifies three core modules: Planner-Critic for high-level plan refinement, Step-Check for intermediate verification, and Actor-Critic for action-level optimization.
  arXiv  Detail & Related papers  (2025-02-12T01:06:10Z)
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents [58.18100825673032]
  This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions.<n>In the OSWorld benchmark, UI-TARS achieves scores of 24.6 with 50 steps and 22.7 with 15 steps, outperforming Claude (22.0 and 14.9 respectively)
  arXiv  Detail & Related papers  (2025-01-21T17:48:10Z)
• Zero-Shot Prompting Approaches for LLM-based Graphical User Interface Generation [53.1000575179389]
  We propose a Retrieval-Augmented GUI Generation (RAGG) approach, integrated with an LLM-based GUI retrieval re-ranking and filtering mechanism.<n>In addition, we adapt Prompt Decomposition (PDGG) and Self-Critique (SCGG) for GUI generation.<n>Our evaluation, which encompasses over 3,000 GUI annotations from over 100 crowd-workers with UI/UX experience, shows that SCGG, in contrast to PDGG and RAGG, can lead to more effective GUI generation.
  arXiv  Detail & Related papers  (2024-12-15T22:17:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.