OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning
This addresses the challenge of non-physical hallucinations in LLMs for scientific applications, offering interpretable reasoning for researchers in physics and engineering.
The paper tackles the problem of large language models struggling with physical dynamics governed by partial differential equations by proposing OMNIFLOW, a neuro-symbolic architecture that grounds multimodal LLMs in physical laws without domain-specific fine-tuning, achieving significant performance improvements in zero-shot generalization and few-shot adaptation across turbulence, Navier-Stokes equations, and weather forecasting benchmarks.
Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous spatiotemporal dynamics governed by Partial Differential Equations (PDEs), often resulting in non-physical hallucinations. Existing approaches typically resort to costly, domain-specific fine-tuning, which severely limits cross-domain generalization and interpretability. To bridge this gap, we propose OMNIFLOW, a neuro-symbolic architecture designed to ground frozen multimodal LLMs in fundamental physical laws without requiring domain-specific parameter updates. OMNIFLOW introduces a novel \textit{Semantic-Symbolic Alignment} mechanism that projects high-dimensional flow tensors into topological linguistic descriptors, enabling the model to perceive physical structures rather than raw pixel values. Furthermore, we construct a Physics-Guided Chain-of-Thought (PG-CoT) workflow that orchestrates reasoning through dynamic constraint injection (e.g., mass conservation) and iterative reflexive verification. We evaluate OMNIFLOW on a comprehensive benchmark spanning microscopic turbulence, theoretical Navier-Stokes equations, and macroscopic global weather forecasting. Empirical results demonstrate that OMNIFLOW significantly outperforms traditional deep learning baselines in zero-shot generalization and few-shot adaptation tasks. Crucially, it offers transparent, physically consistent reasoning reports, marking a paradigm shift from black-box fitting to interpretable scientific reasoning.