AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li + 9 more
TLDR
AutoGen is an open-source framework that enables developers to create complex LLM applications by orchestrating customizable multi-agent conversations combining LLMs, humans, and tools.
Key contributions
- Introduces a flexible multi-agent system where agents converse to collaboratively solve tasks.
- Supports programming agent interactions using both natural language and code for diverse application needs.
- Demonstrates effectiveness across various domains including math, coding, decision-making, and entertainment.
Why it matters
This paper matters because it provides a versatile and extensible infrastructure that leverages multi-agent conversations to unlock more sophisticated and interactive LLM applications, enabling developers to build complex workflows that integrate AI, human input, and external tools seamlessly.
Original Abstract
AutoGen is 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. Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.