AutoGen: Enabling next-Gen LLM Applications via Multi-Agent Conversation
Wu, Qingyun, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang (Eric) Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. 2023. “AutoGen: Enabling next-Gen LLM Applications via Multi-Agent Conversation.” Technical report MSR-TR-2023-33. Microsoft. www.microsoft.com/en-us/research/publication/autogen-enabling-next-gen-llm-applications-via-multi-agent-conversation-framework/
Abstract
We present AutoGen, an open-source framework that allows developers to build LLM applications via multiple agents that can 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. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. We provide many examples to build effective applications for domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.
BibTeX
@techreport{wu2023autogen,
title = {{{AutoGen}}: {{Enabling}} next-Gen {{LLM}} Applications via Multi-Agent Conversation},
author = {Wu, Qingyun and Bansal, Gagan and Zhang, Jieyu and Wu, Yiran and Zhang, Shaokun and Zhu, Erkang (Eric) and Li, Beibin and Jiang, Li and Zhang, Xiaoyun and Wang, Chi},
year = 2023,
month = aug,
number = {MSR-TR-2023-33},
institution = {Microsoft},
url = {https://www.microsoft.com/en-us/research/publication/autogen-enabling-next-gen-llm-applications-via-multi-agent-conversation-framework/},
abstract = {We present AutoGen, an open-source framework that allows developers to build LLM applications via multiple agents that can 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. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. We provide many examples to build effective applications for domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.}
}