What Should an Operating System Do for AI Agents?

An operator should be able to authorize a bounded task once, then let an AI agent complete it without repeated permission prompts. That requires more than a convenient tool interface: delegated authority must remain bounded, resource spending must survive worker failure, and a lost reply must not turn a retry into a duplicate effect. We argue for an operating-system contract organized around jobs whose authority, budgets and operation outcomes persist independently of their workers. OSIOS is an early standalone operating-system project exploring this contract through a capability-based microkernel and resource-owning services. The central research question is not whether a new kernel can run an agent, but what an operating system adds beyond a well-engineered runtime on Linux. We propose a staged comparison of tuned Linux, the same Linux with the OSIOS interface, and an OSIOS guest with that interface. The evaluation separates useful task completion, containment and recovery, and explicitly permits the conclusion that Linux captures all practical benefit. The boot handoff has passed 24 of 24 checks on the tested revision; agent-performance and job-isolation results remain future work.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-20
DOI
https://doi.org/10.5281/zenodo.24393504
Primary Topic
Security and Verification in Computing
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

What Should an Operating System Do for AI Agents?

Yaron Torgeman
1 links
Zenodo (CERN European Organization for Nuclear Research)
Security and Verification in Computing
preprint

What Should an Operating System Do for AI Agents?

Yaron Torgeman
preprint en

Abstract

An operator should be able to authorize a bounded task once, then let an AI agent complete it without repeated permission prompts. That requires more than a convenient tool interface: delegated authority must remain bounded, resource spending must survive worker failure, and a lost reply must not turn a retry into a duplicate effect. We argue for an operating-system contract organized around jobs whose authority, budgets and operation outcomes persist independently of their workers. OSIOS is an early standalone operating-system project exploring this contract through a capability-based microkernel and resource-owning services. The central research question is not whether a new kernel can run an agent, but what an operating system adds beyond a well-engineered runtime on Linux. We propose a staged comparison of tuned Linux, the same Linux with the OSIOS interface, and an OSIOS guest with that interface. The evaluation separates useful task completion, containment and recovery, and explicitly permits the conclusion that Linux captures all practical benefit. The boot handoff has passed 24 of 24 checks on the tested revision; agent-performance and job-isolation results remain future work.

Zenodo (CERN European Organization for Nuclear Research)
Security and Verification in Computing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
What Should an Operating System Do for AI Agents? — Yaron Torgeman · Zenodo (CERN European Organization for Nuclear Research) (2026) | TGRS Research Map | TGRS