agent/papers/items/2026-2606-28061-toolprivacybench-benchmarking-purpose-bound-privacy-in-tool-using-llm-agents.md

Paper: ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents

---

type: paper title: "ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents" authors: Shijing Hu, Liang Liu, Zhu Meng, Zhicheng Zhao year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.28061 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-26 updated_at: 2026-06-26 status: queued relevance: high topics:

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

benchmarks:

models:

datasets:

• cs.CR
• cs.AI related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 22 collection_queries: agent-evaluation, function-calling, llm-agent, tool-use

One-line Takeaway

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

Why Collected

• matched queries: agent-evaluation, function-calling, llm-agent, tool-use
• inferred topics: agent-evaluation, rag, tool-use, workflow-agent
• 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/2606.28061