# Researchers test role-based tool access for AI agents

_Published Friday, September 25, 2026 at 12:15 PM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers have proposed a framework that limits which tools an AI agent can use as it works. Their preprint describes skilder, which gives an agent a small catalog of roles and supplies the tools for a role only after the agent selects it. A server then enforces the limits attached to those tools.

Across 13 tasks tested with six models, the simulated authorization layer executed no unauthorized tool calls or parameter violations when agents completed discovery and made a governed call. Some agents still failed to follow the discovery process or meet response-quality checks, so the result does not establish reliable task completion.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2609.28693)

---
Canonical: https://techandbusiness.org/newswire/4S1ptyXLVwVc8eh_EwEbT4
Published: 2026-09-25T16:15:10.754Z
Story chronology: 2026-09-25T04:00:00.000Z
Retrieved: 2026-09-25T18:18:57.786Z
Publisher: Tech & Business (techandbusiness.org)