Large language models act and interact in the real world
Agentic Large Language Models
Artificial Intelligence
Summary
Large language models (LLMs) can already understand and generate human language, helping us with many tasks like writing or answering questions. This paper explores what happens when LLMs not only generate text but also take actions in the world and communicate with each other directly. The authors explain how these "agentic" LLMs work, the ways they can act autonomously, and how their interactions might affect users. They also discuss what it means for people who use these models and the potential for future developments.
What this means in practice
- •For software developers: Create applications where language models perform tasks autonomously based on user input, improving automation beyond text generation.
- •For enterprise automation teams: Design systems where multiple language-based agents collaborate to manage complex workflows without direct human intervention.
A position paper. It proposes an approach and reports no results.
Authors
Max van Duijn, Michiel van der Meer, Aske Plaat, Niki van Stein
Abstract
Large language models (LLMs) have taken the world by storm. Their ability to communicate with us in our own language, and to reason about our world, has made them a favorite tool for writing, answering questions, and much more. Their answers already influence our decisions and our actions. What would happen if LLMs themselves could act in the world directly? What would happen if LLMs could interact with each other? Agentic LLMs combine the power of large language models with the ability to act in the real world. In this book we will discuss how agentic LLMs work, how they act, how they interact, and what this means for us, as users.