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

Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation arXiv:2512.16310v3 Announce Type: replace-cross Abstract: LLM-based agents increasingly use multiple external tools to complete complex tasks. We study Tools Orchestration Privacy Risk (TOP-R): an agent may combine individually non-sensitive tool returns and disclose an unintended sensitive conclusion. We formalize TOP-R with three conditions: conclusion sensitivity, single-source non-inferability, and compositional infera