agent/papers/items/2026-2605-05704-safeharbor-hierarchical-memory-augmented-guardrail-for-llm-agent-safety.md

Paper: SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

---

type: paper title: "SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety" authors: Zhe Liu, Zonghao Ying, Wenxin Zhang, Quanchen Zou, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang, Hao Peng year: 2026 venue: arXiv url: https://arxiv.org/abs/2605.05704 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-05-07 updated_at: 2026-05-22 status: queued relevance: high topics:

• agent-safety
• computer-use
• memory
• reasoning
• tool-use methods:

benchmarks:

models:

datasets:

• cs.CR
• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 22 collection_queries: agent-safety, autonomous-agent-llm

One-line Takeaway

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

Why Collected

• matched queries: agent-safety, autonomous-agent-llm
• inferred topics: agent-safety, computer-use, memory, reasoning, tool-use
• arXiv categories: cs.CR, cs.AI
• collection score: 22

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/2605.05704