Scholarlink

<p>The prevailing paradigm in AI for physical systems: scaling general-purpose foundation models toward universal multimodal reasoning, confronts a barrier at the control interface. Frontier vision–language models achieve only 50–53% accuracy on basic quantitative physics tasks, behaving as approximate guessers that preserve semantic plausibility while violating physical constraints. Safety-critical control demands outcome-space guarantees over executed actions, not parameter-space imitation. Here, we present what is, to our knowledge, the first demonstration of Agentic Physical AI for nuclear reactor control: a domain-specific foundation model in which a compact language model learns control policies through physics-based simulator validation rather than perceptual inference. The framework unifies three capabilities: <i>Agentic AI</i> generates and selects among admissible control strategies; <i>Physical AI</i> evaluates those strategies through closed-loop execution in a reactor simulator; and a <i>domain-specific foundation model</i> acquires reusable control priors through data scaling. Under nominal simulated conditions, scaling yields regime-dependent gains in reliability, including an approximately 500-fold reduction in outcome variance and elimination of terminal-power excursions above 10% on the sampled distribution. Although trained with balanced exposure to four actuation families, the model concentrates 95% of runtime execution on a single-bank strategy without reinforcement learning or reward engineering. The learning framework transfers across reactor simulators without architectural redesign. These results establish a pathway toward reusable, physics-validated foundation-model intelligence for safety-critical control.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Agentic physical AI toward a domain-specific foundation model for energy systems: a case study on nuclear reactor control

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月5日

查看全文
  • Yoon Pyo Lee,
  • Samrendra Roy,
  • Kazuma Kobayashi,
  • Sajedul Talukder,
  • Diab Abueidda,
  • Seid Koric,
  • Souvik Chakraborty,
  • Syed Bahauddin Alam

摘要

The prevailing paradigm in AI for physical systems: scaling general-purpose foundation models toward universal multimodal reasoning, confronts a barrier at the control interface. Frontier vision–language models achieve only 50–53% accuracy on basic quantitative physics tasks, behaving as approximate guessers that preserve semantic plausibility while violating physical constraints. Safety-critical control demands outcome-space guarantees over executed actions, not parameter-space imitation. Here, we present what is, to our knowledge, the first demonstration of Agentic Physical AI for nuclear reactor control: a domain-specific foundation model in which a compact language model learns control policies through physics-based simulator validation rather than perceptual inference. The framework unifies three capabilities: Agentic AI generates and selects among admissible control strategies; Physical AI evaluates those strategies through closed-loop execution in a reactor simulator; and a domain-specific foundation model acquires reusable control priors through data scaling. Under nominal simulated conditions, scaling yields regime-dependent gains in reliability, including an approximately 500-fold reduction in outcome variance and elimination of terminal-power excursions above 10% on the sampled distribution. Although trained with balanced exposure to four actuation families, the model concentrates 95% of runtime execution on a single-bank strategy without reinforcement learning or reward engineering. The learning framework transfers across reactor simulators without architectural redesign. These results establish a pathway toward reusable, physics-validated foundation-model intelligence for safety-critical control.