Human-Guided Harm Recovery for Computer Use Agents

Computer Science > Artificial Intelligence [Submitted on 20 Apr 2026] Human-Guided Harm Recovery for Computer Use Agents Christy Li, Sky CH-Wang, Andi Peng, Andreea Bobu As LM agents gain the ability to execute actions on real computer systems, we need ways to not only prevent harmful actions at scale but also effectively remediate harm when prevention fails. We formalize a solution to this neglected challenge in post-execution safeguards as harm recovery: the problem of optimally steering an agent from a harmful state back to a safe one in alignment with human preferences. We ground preference-aligned recovery through a formative user study that identifies valued recovery dimensions and produces a natural language rubric. Our dataset of 1,150 pairwise judgments reveals context-dependent shifts in attribute importance, such as preferences for pragmatic, targeted strategies over comprehensive long-term approaches. We operationalize these learned insights in a reward model, re-ranking multiple candidate recovery plans generated by an agent scaffold at test time. To evaluate recovery capabilities systematically, we introduce BackBench, a benchmark of 50 computer-use tasks that test an agent's ability to recover from harmful states. Human evaluation shows our reward model scaffold yields higher-quality recovery trajectories than base agents and rubric-based scaffolds. Together, these contributions lay the foundation for a new class of agent safety methods -- ones that confront harm not only by preventing it, but by navigating its aftermath with alignment and intent. Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2604.18847 [cs.AI]   (or arXiv:2604.18847v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.18847 Focus to learn more Submission history From: Christy Li [view email] [v1] Mon, 20 Apr 2026 21:12:40 UTC (3,430 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)