提出HalluClear工具链，解决GUI代理幻觉问题。
HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
- 构建GUI特异性幻觉分类体系，基于真实故障分析。
- 仅用9000样本微调即显著降低幻觉，提升动作准确性。
- 适合需高可靠性的自动化测试与工业级GUI代理开发。
尽管GUI代理的发展主要依赖大规模训练，但脱离现实的幻觉常导致实际部署中的级联失败。与通用视觉语言模型领域不同，当前GUI代理缺乏聚焦幻觉的细粒度诊断、可靠评估与针对性缓解工具。为填补这一空白，我们提出HalluClear，一套面向GUI代理幻觉缓解的综合性工具链，作为计算密集型扩展的补充。HalluClear包含：(1) 基于实证故障分析构建的GUI特异性幻觉分类体系；(2) 经专家标注基准与集成可信度估计校准的三阶段评估流程，提升VLM作为裁判的可靠性；(3) 基于闭环结构化推理的缓解方案，支持通用代理与专用代理在冷启动初始化下的轻量级持续后训练。在代表性代理与公开基准上的实验表明，仅使用本套件中9000个样本进行后训练，即可显著减少幻觉，提升语义接地性与动作保真度，提供一条高效可靠的GUI自动化路径。
原文摘要 · Abstract (English)
While progress in GUI agents has been largely driven by industrial-scale training, ungrounded hallucinations often trigger cascading failures in real-world deployments.Unlike general VLM domains, the GUI agent field lacks a hallucination-focused suite for fine-grained diagnosis, reliable evaluation, and targeted mitigation.To bridge this gap, we introduce HalluClear, a comprehensive suite for hallucination mitigation in GUI agents as a complement to computation-intensive scaling. HalluClear comprises: (1) a GUI-specific hallucination taxonomy derived from empirical failure analysis; (2) a calibrated three-stage evaluation workflow which enhances VLM-as-a-judge reliability via expert-annotated benchmarking and ensemble credibility estimation; and (3) a mitigation scheme based on closed-loop structured reasoning, enabling lightweight continual post-training with cold-start initialization for both generalist and GUI-specialist agents. Experiments across representative agents and public benchmarks demonstrate that post-training on only 9K samples within our suite can significantly reduce hallucinations, thereby improving grounding and action fidelity, offering a compute-efficient pathway to robust GUI automation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。