Can I Trust You? Advancing GUI Task Automation with Action Trust Score

摘要

Graphical User Interface (GUI) automation holds significant promise for assisting users with complex tasks, thereby enhancing accessibility and productivity. However, existing works mainly concentrate on improving AI agent's capabilities to automate procedures for liberating humans from tedious complexities, lacking the evaluation of potential erroneous agent-generated actions that could lead to task failure and irreversible system damage, inherently involving a degree of risk particularly for fields where automated systems have control over critical operations. To address this issue, we introduce TrustScorer, which evaluates the trustworthiness of actions generated by AI agents, enabling a new human-AI collaboration paradigm in GUI task automation, i.e., actions with low predicted trust scores are redirected for human intervention, thereby mingling human precision with AI efficiency. We further construct TrustBench, which provides diverse real-world GUI automation tasks with per-step ground-truth action sequence and trust score annotations, benchmarking trustworthy GUI task automation. Experimental results show that our designed three types of exploratory TrustScorer methods can help identify erroneous actions and enhance the task success rate (up to 38.1% improvement). Moreover, comprehensive analysis highlights the critical role of action trustworthiness assessment in agent automation and provides valuable insights for future explorations into more advanced trustworthiness scoring techniques to further support the reliable human-AI collaboration. Code and data are available at https://github.com/showlab/TrustScorer.