2023 AutoGenEnablingNextGenLlmApplic

• (Wu, Bansal et al., 2023) ⇒ Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. (2023). “AutoGen: Enabling Next-Gen LLM Applications via Multi-agent Conversation Framework.” In: arXiv preprint arXiv:2308.08155. doi:10.48550/arXiv.2308.08155

Subject Headings: AutoGen, Multi-Agent System.

Notes

• The paper presents the concept of conversable agents, customizable entities that leverage LLMs, tools, and human inputs, allowing developers to create diverse and interactive AI systems.
• The paper pioneers a new programming paradigm called conversation programming, which unifies natural language and code to define agent behaviors and interactions, simplifying the development of intricate workflows.
• The paper showcases the flexibility of AutoGen through six diverse applications, including math problem solving, retrieval-augmented code generation, and conversational chess, demonstrating its versatility across domains.
• The paper provides empirical evidence that AutoGen outperforms existing methods in various tasks, highlighting the benefits of multi-agent collaboration and the framework’s ability to reduce development effort.
• The paper discusses the modularity of AutoGen, emphasizing how its design allows for easy customization, extension, and reuse of agents, promoting efficient application development.
• The paper addresses important ethical considerations, including privacy, bias, and safety, and proposes guidelines for ensuring accountability and transparency in the use of multi-agent LLM systems.

Cited By

• http://scholar.google.com/scholar?q=%222023%22+Autogen%3A+Enabling+Next-gen+Llm+Applications+via+Multi-agent+Conversation+Framework

2023

• (Wang, Ma et al., 2023) ⇒ Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhewei Wei, and Ji-Rong Wen. (2023). “A Survey on Large Language Model based Autonomous Agents.” In: arXiv preprint arXiv:2308.11432. doi:10.48550/arXiv.2308.11432
  • QUOTE: ... To promote the application of LLM-based autonomous agents, researchers have also introduced many open-source libraries, based on which the developers can quickly implement and evaluate agents according to their customized requirements (49, 47, 42, 44, 39, 40, 46, 16, 36, 43, 38, 125, 52, 45, 41, 50, 158). ...

Quotes

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.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2023 AutoGenEnablingNextGenLlmApplic	Chi Wang Qingyun Wu Gagan Bansal Jieyu Zhang Yiran Wu Shaokun Zhang Erkang Zhu Beibin Li Li Jiang Xiaoyun Zhang			AutoGen: Enabling Next-Gen LLM Applications via Multi-agent Conversation Framework				10.48550/arXiv.2308.08155		2023