Declarative Integration and Management of Large Language Models through Finite Automata: Application to Automation, Communication, and Ethics
This provides a general tool for combining LLMs with minimal programming effort, potentially benefiting developers in AI integration tasks, though it appears incremental as it builds on existing automata and event-driven methods.
The authors tackled the problem of efficiently integrating multiple Large Language Models (LLMs) by developing a declarative architecture using finite automata and an event management system to select the best LLM for tasks, demonstrating its flexibility in automation, communication, and ethics applications.
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.