arXiv：cs.AI· Marcos Lima Romero, Ricardo Suyama·· 6 小时前
LLM 智能体发现跨域依赖冲突仍继续执行：网络切片中的实验研究
When LLM Agents See a Conflict but Still Proceed: Cross-Domain Dependencies in Network Slicing
AI 导读
研究通过智能电网用例测试了 LLM 智能体在网络切片中处理跨域依赖的能力，来自四家提供商的十款模型在 600 次运行中，有七款至少在观察到跨域依赖后仍移除了一次保护切片，高危害层级中该比例达 76%，仅一款模型从未移除。研究识别出两种失败模式：未查询依赖，以及查询后仍继续执行，表明仅让依赖可见不足以保障安全，应由管理架构在不可逆操作前强制验证依赖。
正文
Abstract:Future AI-native networks are being designed to apply autonomous agents built on large language models (LLMs) in network management through intents. When intents from different domains meet on the same resource, an agent must recognize the cross-domain dependency before taking an irreversible action. We investigate this problem through a smart-grid use case, in which a power utility holds an active intent on a backup slice for protection traffic. This slice appears idle by design, which is precisely the profile targeted by a cost-reduction intent. We built a tool-based environment in which the dependency must be either queried by the agent or read from an inventory annotation, together with a negative control, and evaluated ten models from four different providers in 600 runs. Most models acted against the dependency they had observed: seven of the ten models removed the protection slice at least once after receiving the cross-domain dependency, and in the high-harm tier the slice was removed in 76% of the exposed runs, while four models practically never did. Only one of ten models never removed the slice. We identify two failure modes, not querying the dependency and querying it but proceeding anyway, and show that agents often reported no conflict after observing it. These results indicate that, in AI-native networks, visibility of cross-domain dependencies is not a sufficient safeguard, and that dependency verification should be enforced by the management architecture before irreversible actions rather than delegated to the LLM's judgment.
| Comments: | Submitted to 11th Workshop on Communication Networks and Power Systems (WCNPS 2026) |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Systems and Control (eess.SY) |
| ACM classes: | I.2.1 |
| Cite as: | arXiv:2610.17118 [cs.AI] |
| (or arXiv:2610.17118v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17118 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Marcos Romero [view email]
[v1]
Mon, 12 Oct 2026 17:10:07 UTC (1,432 KB)
来源：arXiv：cs.AI · arxiv.org