AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
By Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, E. Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu and 4 more. 2023
2,123 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/9ea0757c750ab1222a7442d3485a74d1c526b04c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- Multi-Agent Collaboration Mechanisms: A Survey of LLMs (2025, positive): “Similarly, AutoGen [134] enables developers to define flexible agent behaviors and communication patterns, allowing LLM agents to cooperate through conversation and tackle complex tasks by decomposing them into manageable subtasks.”
- Promises and challenges of generative artificial intelligence for human learning (2024, positive): “This is enabled by advance ments in generative agents—autonomous and adaptive AI entities that operate independently, pursuing objectives without continuous user interaction, as exemplified by tools such as AutoGen 53 .”
- AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025, positive): “This adaptive, memory-driven coordination exemplifies Agentic AI’s potential to reduce labor costs, increase harvest efficiency, and respond to uncertainties in complex agricultural environments surpassing the rigid programming of conventional agricultural robots [100], [157].”
- LLMs Get Lost In Multi-Turn Conversation (2025, positive): “Such processes are typically orchestrated by an agentic framework (such as Autogen [84] or LangChain [8]) that allows system builders to compose workflows with LLM calls as individual blocks.”
- AlphaEvolve: A coding agent for scientific and algorithmic discovery (2025, neutral): “Other recent work [108] has also proposed the use of multiple LLM agents that converse with each other to accomplish mathematical and coding tasks.”
- Why Do Multi-Agent LLM Systems Fail? (2025, neutral): “Adapting verification across domains remains an ongoing research challenge.”
- GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design (2026, unknown): “The open-source AutoGen framework [42] was used to facilitate the multi-agent pipeline, enabling both automated LLM-driven generation and tool usage, such as querying the knowledge graphs.”
- Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI (2025, unknown): “Recent frameworks like HuggingGPT [4], AutoGen [7], and MetaGPT [8] demonstrate sophisticated orchestration patterns where a central coordinator routes tasks to specialized agents based on their capabilities.”
- LLM as a Broken Telephone: Iterative Generation Distorts Information (2025, unknown): “We consider the implications for multi-agent settings, where communication frameworks leverage collaborative interactions between multiple LLMs (Park et al., 2023; Wu et al., 2023; Li et al., 2024b).”
- Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows (2025, unknown): “Large language models (LLMs) have catalyzed the development of agentic systems capable of executing complex, multi-step tasks autonomously (Hong et al., 2024; Wu et al., 2024; Xi et al., 2024; Mialon et al., 2024).”