The Irreversibility Budget: Fleet-Level Risk Accounting and Admission Control for Agent Operating Systems
arXiv cs.AIen
arXiv:2609.00275v1 Announce Type: new Abstract: Fleets of LLM agents now externalize effects that cannot be fully undone: they move money, deploy code, delete data, and disclose information. Current controls check one effect at a time, so a fleet of individually authorized agents can overdraw its principal's risk under a shared trigger while every local gate stays correct. We propose the irreversibility budget, a cumulative account of residual value-at-risk that a trusted runtime maintains for each principal across agents, workflows, and tenants. Treating irreversibility as a first-class resource, the runtime charges each effect its residual loss below the agent and denies the marginal effec
This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.
Read the full story at arXiv cs.AI- Forskning
- Agenter
Related AI news
- Tencent’s Hy4 model gains in open-source AI rankings after ecosystem-driven trainingSCMP Tech · September 2, 2026
- KI-Agenten führen git-Schadcode beim Starten automatisch ausheise online – KI · September 2, 2026
- Anzeige: Ansible-Workshop: Konfigurationsmanagement ohne AgentGolem.de · September 2, 2026
- UI-Venus-2 Technical ReportarXiv cs.AI · September 2, 2026
- When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal EstimationarXiv cs.AI · September 2, 2026
- MiNER: Fine-Tuned Biomedical Natural Language Processing for Malaria Disease Entity Recognition in Clinical TextsarXiv cs.AI · September 2, 2026