Skip to content
AI Atlas
PaperActive

Can AI Agents Detect and Repair Artifact Drift in Network Experiments?

arxiv.org/abs/2609.09849

Updated 51 min ago · first seen 11 Sept 2026

paper_01M294GMWWZ856A4DAW4JAP4N6

Published
11 Sept 2026
T1 · 51 min ago
arXiv
2609.09849
T1 · 51 min ago
Category
cs.NI
T1 · 51 min ago

Abstract

In recent years, AI agents have evolved into capable assistants that carry out multi-step tasks in digital environments. The network systems community is beginning to explore these capabilities in operational and experimental settings. However, an agent operating in network systems should not be judged solely by whether it completes the immediate task. The experiment record it modifies must also remain trustworthy. We call this property artifact integrity: the record's claims must remain supported by the available evidence, confined to the scope established by that evidence, and traceable through the artifacts that encode their support. To make this property measurable, we introduce NetArtifactBench, which tests whether AI agents can repair inconsistent records derived from public network-system artifacts while preserving claims that remain supported. The benchmark contains 52 instances with injected inconsistencies ranging from direct contradictions to unstated relations spread across several artifacts. We evaluate 23 agent configurations across three general-purpose AI agent runtimes using deterministic scoring. The average contract pass rate is 65.3 % across 5,980 outputs, but no agent runtime exceeds 30 % when repair requires recovering implicit relations and propagating changes across artifacts. These results reveal a sharp boundary between local correction and complete record-level repair. Therefore, we argue that artifact integrity should become a first-class design and evaluation requirement for AI agents operating on network systems.

Authors 7

Tianzhu Zhang, Weichen Tao, Changgang Zheng, Yusheng Zheng, Long Chen, Xiaoyi Fan, Meikang Qiu

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Arxiv announce type
cross

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

arXiv id
2609.09849

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Categories
cs.NI, cs.AI, cs.SY, eess.SY

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Primary category
cs.NI

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 51 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

51 min ago

Conflicts

None