← Back to all news
arXiv AI By Tianzhu Zhang, Chih-Kai Huang, Meikang Qiu

Can AI Agents Deliver Verifiable Network-Wide Outcomes Across Authority Boundaries?

Read the original on arXiv AI →

The paper introduces EvidenceNet, a runtime assurance layer designed to verify that coordinated AI agent operations achieve an operator’s intended network-wide outcomes across multiple administrative domains. EvidenceNet collects post-change observations from the required authority scopes, checks their freshness and validity, and uses a verifier agent to assess observation content. Experiments on live routing networks demonstrate that this approach can detect successful outcomes that configuration-action logs alone miss, and it rejects completions when observations are sourced incorrectly, substituted, or stale.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Aug 24

Testing and Evaluation of Agentic AI Systems In Military Command and Control

The paper examines how agentic AI systems intended for military command and control are tested and evaluated. It reviews 240 testing practices across eight dimensions and three lifecycle stages, uncovering eight assumptions—grouped into system specifiability, stability, composability, and supervisability—whose validity is weakened by agentic properties. Consequently, test results may meet procedural standards but do not guarantee that fielded behavior matches tested behavior, leading the authors to propose ten assurance claims and suggest that uncertainty be managed through deployment‑time monitoring and defined expiry conditions.

By Ulysse Richard, Heather Frase, Sarah Cao, Di Cooke, Sebastian Kwon, Adrianna Tan
agents
More like this →
arXiv AI
Oct 1

Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents

The paper introduces Runtime Assurance Contracts (RAC) as a formal policy framework for high‑risk AI agents, addressing the "assurance‑transition gap" by binding autonomy boundaries, component eligibility, evidence state, transition policy, human‑review capacity, and non‑compensatory gates. RAC allows soft metrics to influence routing while mandating retries, switches, escalations, deferrals, or stops when mandatory gates fail or are unknown, ensuring aggregate performance cannot alone authorize action. The authors define the contract, evidence record, permission rule, and five invariants, and evaluate RAC through deterministic failure‑injection studies, hand‑authored traces, and a prospective synthetic holdout, comparing it to score‑only and restricted protocol baselines.

By Serhii Zabolotnii
llmsagentsbenchmarkssafety
More like this →
arXiv AI
Aug 20

One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI

The paper investigates how multiple pre‑action controls—authority, resource, and evidence gates—interact in agentic AI systems. It formalizes remediation‑induced control coupling, showing that remediation can invalidate earlier judgments and that the order of remediation matters. The authors propose a remediate‑and‑regate protocol to restore soundness, analyze non‑commuting remediation operators, and demonstrate the approach on a deterministic open‑data artifact with three published engines.

By Gaston Besanson
agents
More like this →