agent/papers/items/2026-2602-13379-unsafer-in-many-turns-benchmarking-and-defending-multi-turn-safety-risks-in-tool.md

Paper: Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents

---

type: paper title: "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents" authors: Xu Li, Simon Yu, Minzhou Pan, Yiyou Sun, Bo Li, Dawn Song, Xue Lin, Weiyan Shi year: 2026 venue: arXiv url: https://arxiv.org/abs/2602.13379 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-02-13 updated_at: 2026-06-10 status: queued relevance: high topics:

• agent-evaluation
• agent-safety
• rag
• tool-use methods:

benchmarks:

models:

datasets:

• cs.CR
• cs.AI
• cs.CL
• cs.LG
• cs.SE related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 15 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, rag, tool-use
• arXiv categories: cs.CR, cs.AI, cs.CL, cs.LG, cs.SE
• collection score: 15

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/2602.13379