agent/papers/items/2026-2605-06992-why-does-agentic-safety-fail-to-generalize-across-tasks.md

Paper: Why Does Agentic Safety Fail to Generalize Across Tasks?

---

type: paper title: Why Does Agentic Safety Fail to Generalize Across Tasks? authors: Yonatan Slutzky, Yotam Alexander, Tomer Slor, Yoav Nagel, Nadav Cohen year: 2026 venue: arXiv url: https://arxiv.org/abs/2605.06992 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-05-07 updated_at: 2026-05-07 status: queued relevance: high topics:

• agent-safety
• embodied-agent methods:

benchmarks:

models:

datasets:

• cs.LG
• stat.ML related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 14 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-safety, embodied-agent
• arXiv categories: cs.LG, stat.ML
• collection score: 14

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/2605.06992