用有限状态机实现大模型的声明式集成与管理
Declarative Integration and Management of Large Language Models through Finite Automata: Application to Automation, Communication, and Ethics
- 通过有限状态机+事件系统，声明式编排多个大模型
- 支持共享历史和任务触发，自动选择最适配模型
- 适合需要多模型协作的自动化、伦理审查等场景
本文提出一种创新架构，通过构建有限状态机并结合事件管理系统，实现大语言模型（LLMs）的声明式组合与共享历史管理，并能根据触发条件自动识别最适合当前任务的LLM。该方法通用且无需大量编程，特别适用于将积极心理学方法整合至AI系统。通过自动化、通信和伦理三个实际应用案例验证了技术的灵活性与高效性。
原文摘要 · Abstract (English)
This article introduces an innovative architecture designed to declaratively combine Large Language Models (LLMs) with shared histories, and triggers to identify the most appropriate LLM for a given task. Our approach is general and declarative, relying on the construction of finite automata coupled with an event management system. The developed tool is crafted to facilitate the efficient and complex integration of LLMs with minimal programming effort, especially, but not only, for integrating methods of positive psychology to AI. The flexibility of our technique is demonstrated through applied examples in automation, communication, and ethics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。