HalluClear：诊断、评估和缓解GUI代理中的幻觉
HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
AI总结：
HalluClear通过引入专门的幻觉分类、校准的评估流程和闭环推理方案，有效减少GUI代理中的幻觉，提升自动化可靠性。
摘要：
尽管GUI代理的进步主要由大规模训练推动，但缺乏专门针对幻觉的诊断、评估和缓解工具。HalluClear引入了基于经验失败分析的GUI特定幻觉分类，校准的三阶段评估流程以及基于闭环结构推理的缓解方案，通过专家标注基准和集 credibility 估计提升 VLM-as-a-judge 的可靠性。实验表明，仅使用9K样本进行微调即可显著减少幻觉，提升接地性和行动准确性，为稳健的GUI自动化提供计算高效的路径。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
