arXiv cs.MA· Abderaouf Bahi, Hasan Masrur·· 9 小时前AI 评分29
GridAnchor:用多智能体 AI 防护自主能源系统免受信息物理幻觉影响
GridAnchor: Specialized Multi-Agent AI for Safeguarding Autonomous Energy Systems Against Cyber-Physical Hallucinations
AI 导读
GridAnchor 是一个面向自主能源系统的验证层,用 Physics-Residual Graph Transformer 对预测器、状态估计器和调度器等智能体的每条输出打分,并结合 Mondrian conformal p 值与 Benjamini-Hochberg 过程做出判定。
正文 · 原文
Abstract:Autonomous energy systems increasingly chain specialized learned agents, such as a forecaster, a state estimator and a dispatcher that may be a language model. These agents can emit confident outputs that contradict physics, and downstream agents may act on them. We define such cyber-physical hallucinations and their cascades, organize them in eight types, and build CPH-Bench, a generator of labeled episodes on SimBench feeders. We propose GridAnchor, a verification layer whose Physics-Residual Graph Transformer scores every claim from residuals between the claims, the measurements and a linearized grid model. Mondrian conformal p-values with the Benjamini-Hochberg procedure turn the scores into decisions, a root head attributes cascades, and a quadratic program repairs unsafe actions with a voltage margin calibrated at repaired steps. On a simulated rural medium-voltage feeder, GridAnchor reaches a message-level area under the precision-recall curve of 0.846, against 0.837 for the strongest of six baselines, a difference within the confidence interval. It leads on estimates and actions, whereas a self-consistency check that knows the label tolerances reaches 0.874 by leading on forecasts. The false-alarm rate stays within 0.17 percentage points of the nominal level on steps without injected hallucinations. In closed loop, GridAnchor leaves no bus outside the voltage band on the test days, against 0.0700% of the bus-steps without protection, and simpler detectors with the same mitigation come close. Stale but coherent messages and single-bus forecast errors remain mostly undetected.
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.25158 [cs.MA] |
| (or arXiv:2611.25158v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2611.25158 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Abderaouf Bahi [view email]
[v1]
Wed, 18 Nov 2026 20:36:22 UTC (55 KB)
来源:arXiv cs.MA · arxiv.org