Metraipolis › archive › dc_49f02b345280

Towards Elastic Least Privilege for Agent Planning — arXiv:2610.40981

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40981
License (as archived)
CC0-1.0
Archived
2026-11-03T05:39:45.029Z
SHA-256 of the archived text
8439780e9d36f4fdce435955bcf0f6c7a205b8cdd057dfcecc5c98d26981805c
Stable URL of this page
https://metraipolis.com/documento/dc_49f02b345280

How to cite

Towards Elastic Least Privilege for Agent Planning — arXiv:2610.40981 — arXiv (en), https://arxiv.org/abs/2610.40981 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49f02b345280 (Metraipolis archive dc_49f02b345280, sha256 8439780e9d36f4fdce435955bcf0f6c7a205b8cdd057dfcecc5c98d26981805c)
BibTeX
@misc{dc49f02b345280,
  title = {Towards Elastic Least Privilege for Agent Planning — arXiv:2610.40981},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40981},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49f02b345280; sha256 8439780e9d36f4fdce435955bcf0f6c7a205b8cdd057dfcecc5c98d26981805c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40981. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

General-purpose AI agents require authority that changes between tasks and during execution. Common deployments trade broad permissions that expose unnecessary authority and narrow permissions that raise approval requests. Existing mechanisms can enforce dynamic authority, but agent tool interfaces rarely provide the agent's planner, the component that chooses its actions, a means of comparing the authority required by alternative actions or of seeing the cost of the authority it already holds. Drawing on the rich history of access control research, we propose the concept of \emph{elastic least privilege}, in which an agent begins with a small baseline of authority and may acquire more within an owner-defined envelope. Elevations are leased and measured against a replenishing budget. Their cost increases with power, proximity to mandatory safety invariants, and repeated requests. Costs are visible to the planner, which can prefer lower-privilege choices and release authority it no longer needs. Authority returns automatically to the baseline when a lease expires, when it is released, or when the budget is exhausted, while persistent legitimate demand may prompt an owner-approved change to the baseline. Building on prior risk-priced and budget-aware access control, we redesign these mechanisms for agents. How best to implement the approach and how well it works in practice are open research questions. In this paper, we present how the approach could work, illustrate the model, and set an open research agenda.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.40981 — 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 2026-11-03T05:23:42.972Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).