Abstract:

To address the issue of low efficiency in generating traditional army tactical combat simulation scenarios, an automated generation method based on large language models is proposed. The large language model invokes a semantic segmentation algorithm to parse and restructure the combat scenario, forming semantic modules. Utilizing a multi-agent collaborative framework based on the model contextual protocol, the large language model drives each agent to extract simulation elements from the corresponding semantic modules, constructing a knowledge graph of scenario elements. Using this knowledge graph as a retrieval medium, the method employs a dense retrieval algorithm to achieve precise matching between simulation scenario data and simulation scenario segment templates, enabling the parallel generation of simulation scenario segments. The large language model integrates these segments into a complete combat simulation scenario. In experiments conducted on a specific test set, the proposed method demonstrates significant advantages over baseline approaches in terms of scenario generation efficiency and the accuracy of scenario elements, offering a feasible practical solution for the efficient generation of combat simulation scenarios.

Key words: combat scenario, combat simulation scenario, large language models, agents, knowledge graph