arXiv Artificial Intelligence

PACE: Provenance-Aware Capability Enforcement for Tool-Using LLM Agents

2 hours ago 02.10.2026 07:00 👁 2 views
PACE: Provenance-Aware Capability Enforcement for Tool-Using LLM Agents

Quick summary

arXiv:2610.01349v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents turn generated text into real side effects, so poisoned tool metadata, retrieved pages, memory, and reusable skills can steer the next call. Vetting an artifact before admission does not settle this. A safe variant and a leaking variant can produce the same admission evidence, and a sound gate then cannot relax that site for either. We make that condition precise, which leaves the last boundary a deployment can still act on. We present Provenance-Aware Capability Enforcement (PACE), which mediates ev

Key takeaways

  • arXiv:2610.01349v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents turn generated text into real side effects, so poisoned tool metadata, retrieved pages, memory, and reusable skills can steer the next call.
  • Vetting an artifact before admission does not settle this.
  • A safe variant and a leaking variant can produce the same admission evidence, and a sound gate then cannot relax that site for either.

Why it matters

This development shows AI moving deeper into everyday software. Productivity potential should be weighed against price, data permissions, exportability and the preservation of human control.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗