BaZi-Based Character Simulation Benchmark: Evaluating AI on Temporal and Persona Reasoning
This addresses the problem of scalable and coherent character simulation for games, storytelling, and virtual reality, though it is domain-specific and incremental in its integration approach.
The paper tackles the challenge of generating realistic virtual characters by creating a BaZi-based QA dataset for persona reasoning and proposing a BaZi-LLM system that integrates symbolic reasoning with large language models, achieving a 30.3%-62.6% accuracy improvement over mainstream LLMs.
Human-like virtual characters are crucial for games, storytelling, and virtual reality, yet current methods rely heavily on annotated data or handcrafted persona prompts, making it difficult to scale up and generate realistic, contextually coherent personas. We create the first QA dataset for BaZi-based persona reasoning, where real human experiences categorized into wealth, health, kinship, career, and relationships are represented as life-event questions and answers. Furthermore, we propose the first BaZi-LLM system that integrates symbolic reasoning with large language models to generate temporally dynamic and fine-grained virtual personas. Compared with mainstream LLMs such as DeepSeek-v3 and GPT-5-mini, our method achieves a 30.3%-62.6% accuracy improvement. In addition, when incorrect BaZi information is used, our model's accuracy drops by 20%-45%, showing the potential of culturally grounded symbolic-LLM integration for realistic character simulation.