LLM-Guided Planning for Multi-hop Reasoning over Multimodal Nuclear Regulatory Documents

Reviewing nuclear regulatory documents requires multi-hop reasoning across tens of thousands of pages, where judgments depend on evidence assembled across multiple chapters. We frame this task as planning: an LLM-based agent observes the evidence collected so far, picks the next document fragment to inspect, and stops when the evidence is sufficient. The agent operates over a vectorless document tree using browse, read, and search tools, and maintains a dynamic knowledge graph (KG) as state. On a 200-question benchmark over NuScale Final Safety Analysis Report (FSAR) documents, the system reaches 81.5% accuracy with a RAGAS Faithfulness of 0.93. The dominant performance factor is planning: against PageIndex, which uses the same document tree without state-conditioned action selection, the gap is +38.0pp (43.5% to 81.5%, p<0.001). The system also outperforms LightRAG (73.0%, p<0.05), HippoRAG (70.5%, p<0.01), and GraphRAG (49.5%, p<0.001), and matches RAPTOR (75.5%, p=0.11) without offline indexing. Edge inference adds 2.8x cost without raising accuracy; we retain it as a traceability module. Of 7,391 inferred edges, 3 Violates edges (0.04%) flag scope boundaries (Q058) and partial conformance (Q176) as typed annotations that a human reviewer can audit.

Deep learning for determining a near-optimal topological design without any iteration

In this study, we propose a novel deep learning-based method to predict an optimized structure for a given boundary condition and optimization setting without using any iterative scheme. For this purpose, first, using open-source topology optimization code, datasets of the optimized structures paired with the corresponding information on boundary conditions and optimization settings are generated at low (32 x 32) and high (128 x 128) resolutions. To construct the artificial neural network for the proposed method, a convolutional neural network (CNN)-based encoder and decoder network is trained using the training dataset generated at low resolution. Then, as a two-stage refinement, the conditional generative adversarial network (cGAN) is trained with the optimized structures paired at both low and high resolutions, and is connected to the trained CNN-based encoder and decoder network. The performance evaluation results of the integrated network demonstrate that the proposed method can determine a near-optimal structure in terms of pixel values and compliance with negligible computational time.