agent/papers/items/2026-2604-18847-human-guided-harm-recovery-for-computer-use-agents.md

Paper: Human-Guided Harm Recovery for Computer Use Agents

---

type: paper title: Human-Guided Harm Recovery for Computer Use Agents authors: Christy Li, Sky CH-Wang, Andi Peng, Andreea Bobu year: 2026 venue: arXiv url: https://arxiv.org/abs/2604.18847 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-04-20 updated_at: 2026-05-28 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• computer-use
• memory
• planning
• rag
• tool-use methods:

benchmarks:

models:

datasets:

• cs.AI
• cs.CL related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 18 collection_queries: agent-safety

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: agent-safety
• inferred topics: agent-evaluation, agent-safety, computer-use, memory, planning, rag, tool-use
• arXiv categories: cs.AI, cs.CL
• collection score: 18

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2604.18847