Metraipolis › archive › dc_7e03e97b4859
Airlock: Bounding the Multi-Agent Blast Radius via Selective Online Containment — arXiv:2611.06727
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06727
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:16:22.399Z
- SHA-256 of the archived text
b052641ca780f91d91ef5f10ad9f125be4adff417a2fd97a5a6cb41db9a43267- Stable URL of this page
https://metraipolis.com/documento/dc_7e03e97b4859
How to cite
Airlock: Bounding the Multi-Agent Blast Radius via Selective Online Containment — arXiv:2611.06727 — arXiv (en), https://arxiv.org/abs/2611.06727 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e03e97b4859 (Metraipolis archive dc_7e03e97b4859, sha256 b052641ca780f91d91ef5f10ad9f125be4adff417a2fd97a5a6cb41db9a43267)
BibTeX
@misc{dc7e03e97b4859,
title = {Airlock: Bounding the Multi-Agent Blast Radius via Selective Online Containment — arXiv:2611.06727},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06727},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e03e97b4859; sha256 b052641ca780f91d91ef5f10ad9f125be4adff417a2fd97a5a6cb41db9a43267},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06727. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
When multi-agent systems act on the external world, a single agent's faulty output can spread across tasks before detection, creating a system-wide blast radius. Single-agent guardrails are confined to individual harnesses, while existing multi-agent controls either cancel only the faulty source and miss downstream consumers or halt and roll back the entire workflow at the cost of healthy work. We present Airlock, a multi-agent runtime and guardrail for selective post-alert fault containment. Its tree-structured runtime, EdgeCitadel, narrows permissions vertically from parent to child agents to establish node boundaries and control switches. Meanwhile, an append-only provenance DAG records cross-agent data consumption horizontally. Upon an alert, Airlock traces forward on this DAG to isolate tainted executions and pending actions, and backward to narrow root causes. At the site switches, a default full quarantine tier freezes affected branches without a solver, while an assured optimized cut tier uses fence-then-prune to enforce a deadline-aware minimum cut minimizing collateral disruption. Across 1,832 testbed runs, 161 physical smart-home LLM runs, and 24,266 simulation records, Airlock blocks all post-alert faulty actuations on our main testbed and smart-home grids with zero post-convergence leaks. Whereas native controls in A2A and LangGraph either contain at most 33.3% of faults or retain at most 16% of work without redo, Airlock retains +68 pp to +96 pp more healthy work, and its optimized cut retains +46 pp more than full quarantine under dense spread. These results show that co-designing runtime authority boundaries with online provenance enables surgical fault containment without sacrificing healthy work (code: this https URL ). Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2611.06727 — 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 2026-11-05T18:10:09.308Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).