📄 中文摘要
在社交网络模拟中，配置数百个 AI 代理是一项繁重的任务。每个代理需要设定活动时间表、发布频率、响应延迟、影响权重和立场等参数。手动完成这些配置不仅不可行，还会耗费大量时间。MiroFish 通过 LLM 驱动的配置生成来自动化这一过程，系统能够分析用户的文档和知识图谱，从而高效生成所需的代理配置。
如何使用 LLMs 批处理生成超过 100 种代理配置
📄 English Summary
Cómo generar +100 configuraciones de agentes usando LLMs con procesamiento por lotes
Configuring hundreds of AI agents for social network simulations can be an overwhelming task. Each agent requires settings for activity schedules, posting frequencies, response delays, influence weights, and stances. Manually configuring these parameters is impractical and time-consuming. MiroFish automates this process using LLM-driven configuration generation, allowing the system to analyze user documents and knowledge graphs to efficiently generate the required agent configurations.