Metraipolis › archive › dc_a653e60e30af
Agentao: A Policy-Governed Runtime Harness for Embeddable Tool-Using LLM Agents — arXiv:2608.13574
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13574
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:19:28.764Z
- SHA-256 of the archived text
1607a1a9cf5d6d6ca5f8ec84ba452ff4b156fcf3e8b7de8628e984fc1e0a89ef- Stable URL of this page
https://metraipolis.com/documento/dc_a653e60e30af
How to cite
Agentao: A Policy-Governed Runtime Harness for Embeddable Tool-Using LLM Agents — arXiv:2608.13574 — arXiv (en), https://arxiv.org/abs/2608.13574 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a653e60e30af (Metraipolis archive dc_a653e60e30af, sha256 1607a1a9cf5d6d6ca5f8ec84ba452ff4b156fcf3e8b7de8628e984fc1e0a89ef)
BibTeX
@misc{dca653e60e30af,
title = {Agentao: A Policy-Governed Runtime Harness for Embeddable Tool-Using LLM Agents — arXiv:2608.13574},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13574},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a653e60e30af; sha256 1607a1a9cf5d6d6ca5f8ec84ba452ff4b156fcf3e8b7de8628e984fc1e0a89ef},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13574. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM agents increasingly operate as execution systems that invoke tools, modify local state, use persistent memory, and interact with external protocols. These capabilities make agents useful, but they also introduce risks related to over-privileged actions, weak auditability, prompt injection, tool poisoning, and uncontrolled side effects. This paper presents Agentao, a governed local-first runtime for tool-using LLM agents. Agentao separates model-generated action proposals from host-authorized execution through a layered architecture consisting of host-facing surfaces, a host contract, a runtime core, a permission-mediated tool system, and supporting subsystems for memory, replay, plugins, skills, sub-agents, and protocol integration. We describe the motivation, threat model, design goals, governance model, execution pipeline, and structured event interface of the system. Agentao does not provide formal safety guarantees; rather, it demonstrates how permissions, state, protocol boundaries, and execution traces can be made explicit runtime abstractions for building agents that are more governable, inspectable, and suitable for host-controlled local environments. The code is publicly available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.MA). Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2608.13574 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T02:01:30.009Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).