AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversations

Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, Chi Wang

Research Area: LMs and interactions

Keywords: Large Language Model, Multi-Agent Conversation Framework, Open-Source Library

TL;DR: AutoGen is an open-source framework that allows developers to build LLM applications using multiple conversable agents and conversation programming. Experiments show benefits on diverse domains.

Abstract: We present AutoGen, an open-source framework that allows developers to build LLM applications by composing multiple agents to converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. It also enables developers to create flexible agent behaviors and conversation patterns for different applications using both natural language and code. AutoGen serves as a generic infrastructure and is widely used by AI practitioners and researchers to build diverse applications of various complexities and LLM capacities. We demonstrate the framework’s effectiveness with several pilot applications, with domains ranging from mathematics and coding to question-answering, supply-chain optimization, online decision-making, and entertainment.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 1328