arXiv Artificial Intelligence

Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation

7 days ago 03.09.2026 07:00 👁 1 views
Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation

Quick summary

arXiv:2512.16310v4 Announce Type: replace-cross Abstract: LLM agents can combine individually non-revealing tool returns and disclose a sensitive conclusion, creating Tools Orchestration Privacy Risk (TOP-R). We formalize TOP-R through three conditions: conclusion sensitivity, single-source non-inferability, and compositional inferability. We introduce Library-Grounded Reverse-Inference Seed Expansion (LRSE), a four-library reverse-construction pipeline, and use it to build TOP-Bench, a 1,000-instance benchmark evaluated under a controlled two-stage tool-use protocol. Across six LLM agents, av

Key takeaways

  • arXiv:2512.16310v4 Announce Type: replace-cross Abstract: LLM agents can combine individually non-revealing tool returns and disclose a sensitive conclusion, creating Tools Orchestration Privacy Risk (TOP-R).
  • We formalize TOP-R through three conditions: conclusion sensitivity, single-source non-inferability, and compositional inferability.
  • We introduce Library-Grounded Reverse-Inference Seed Expansion (LRSE), a four-library reverse-construction pipeline, and use it to build TOP-Bench, a 1,000-instance benchmark evaluated under a controlled two-stage tool-use protocol.

Why it matters

“Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation” highlights the need for repeatable measurement rather than a single impressive demonstration. Independent validation across datasets and clearly stated limitations determine whether a result can guide product decisions.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗