In aerodynamic design, high-quality multiblock mesh generation serves as the cornerstone for accurate lift-drag analysis of wings. However, conventional computational fluid dynamics (CFD) workflows offered by industrial software reveals critical limitations in labor-intensive manual operations. While automatic meshing in 2D wing cross-section is well-established, its extension to 3D wing meshing faces unresolved challenges, including excessive block generation, complex feature alignment, and incomplete simulation-ready pipelines. This paper presents an automatic multiblock mesh generation framework specifically targeting these commercial software shortcomings for 3D wing analysis. Our methodology addresses three persistent challenges: (1) a parameterization-based tip surface meshing method with optimized cell quality, (2) an extrusion-based wing body meshing approach ensuring precise feature alignment at joints and leading edges, and (3) an end-to-end pipeline from geometric pre-processing to CFD-ready multiblock mesh generation. Experiments demonstrate the framework’s ability to produce high-quality meshes with minimal manual intervention, streamlining the workflow for aerodynamic simulations.

To address the complexity and high manual dependency in behavior modeling process for cooperative combat simulation scenarios, this paper integrates Large Language Model (LLM) technology to enable intelligent modeling of aircraft formation cooperative combat behaviors. A hybrid hierarchical modeling framework integrating LLM technology is proposed to enable a semantics-driven and automated modeling workflow. A two-layer ‘system-user’ prompt engineering method is designed to transform conceptual semantics into formalized state machines. A vector-retrieval-based association method is developed to achieve intelligent and efficient matching between decision states and behavior tree nodes. Based on these methods, representative cooperative combat behavior models for aircraft formations are constructed and validated through simulation experiments in typical combat scenarios. The experimental results demonstrate that the proposed framework and methods effectively support rapid and intelligent modeling of cooperative combat behaviors, confirming their applicability and practical effectiveness.

Reinforcement Learning (RL) has emerged as a promising data-driven solution for wargaming decision-making. However, two domain challenges still exist: (1) dealing with discrete-continuous hybrid wargaming control and (2) accelerating RL deployment with rich offline data. Existing RL methods fail to handle these two issues simultaneously, thereby we propose a novel offline RL method targeting hybrid action space. A new constrained action representation technique is developed to build a bidirectional mapping between the original hybrid action space and a latent space in a semantically consistent way. This allows learning a continuous latent policy with offline RL with better exploration feasibility and scalability and reconstructing it back to a needed hybrid policy. Critically, a novel offline RL optimization objective with adaptively adjusted constraints is designed to balance the alleviation and generalization of out-of-distribution actions. Our method demonstrates superior performance and generality across different tasks, particularly in typical realistic wargaming scenarios.