Metraipolis › archive › dc_3fa6ef2fa513

Safety Signals to Verify NetOps Agents with Action-Level Granularity — arXiv:2609.14422

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.14422
License (as archived): CC0-1.0
Archived: 2026-10-15T22:47:30.312Z
SHA-256 of the archived text: 654e1538d892c664d82a0c72c967f5ff1e4859eb2e17cb7a332ea770b33f888e
Stable URL of this page: https://metraipolis.com/documento/dc_3fa6ef2fa513

How to cite

Safety Signals to Verify NetOps Agents with Action-Level Granularity — arXiv:2609.14422 — arXiv (en), https://arxiv.org/abs/2609.14422 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3fa6ef2fa513 (Metraipolis archive dc_3fa6ef2fa513, sha256 654e1538d892c664d82a0c72c967f5ff1e4859eb2e17cb7a332ea770b33f888e)

BibTeX

@misc{dc3fa6ef2fa513,
  title = {Safety Signals to Verify NetOps Agents with Action-Level Granularity — arXiv:2609.14422},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14422},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3fa6ef2fa513; sha256 654e1538d892c664d82a0c72c967f5ff1e4859eb2e17cb7a332ea770b33f888e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14422. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic Network Operations (NetOps) are an emerging paradigm promising to enable workload-aware, self-adjustable, and reliable autonomous networks. While agents have proven their value in incident summarization and telemetry signal extraction, their effectiveness as autonomous control-loop engines heavily relies on their long-horizon reliability. One such setting is the datacenter fabric, where an agent must respond to alarms and operator intents while abstaining from high-risk actions that may cause or extend downtime. Abstention, however, presupposes that an action's impact is known pre-execution, which necessitates a per-action ground truth that NetOps agent benchmarks do not provide. We construct such a ground truth for the network repair task of NetArena. A symbolic replay of the emulated network, validated against the environment at every turn, yields the exact value of every action. From the action-level value, we derive two pre-execution targets, namely whether an action reduces the repair distance (progress) and whether it increases it (harm). We show across 10 agent models, that agent verifiers leveraging internal signals predict both harm and progress more reliably than a baseline using observable signals only. Perspectively, we aim to use these signals as safety feedback to an agent harness to abstain from risky actions and protect the target system.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.14422 — 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 2026-10-15T22:29:03.183Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).