AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework

By Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, Chi Wang. arXiv.org, 2023

1,042 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/1a4c6856292b8c64d19a812a77f0aa6fd47cb96c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A survey on large language model based autonomous agents (2023, unknown): “General Autonomous AI Agent: A number of open source projects based on LLM development have conducted preliminary explorations of Artificial General Intelligence(AGI), they are dedicated to the autonomous universal AI agent framework [45, 43, 38, 40, 35, 36, 42, 15, 32, 39, 34, 114, 47, 41, 37, 46, ”
Large Language Models for Education: A survey and outlook (2024, unknown): “Examples of these applications are illustrated on the left side of Figure 2.”
SGLang: Efficient Execution of Structured Language Model Programs (2023, unknown): “Several LLM programming and agent frameworks exist, such as Guidance [13], LMQL [4], DSPy [20], LangChain [24], AutoGen [55], and LLM Compiler [21].”
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression (2023, background): “…Learning (ICL) (Min et al., 2022; Dong et al., 2023), Retrieval Augment Generation (RAG) (Lewis et al., 2020; Asai et al., 2024), and Multi-turn Agent (Shen et al., 2024; Park et al., 2023; Wu et al., 2023a) are driving prompts to be increasingly longer, even reaching thousands of to-kens.”
A Survey on Large Language Models for Code Generation (2024, unknown): “It combines data from multiple sources, where training data predate the evaluation problems, adds additional tests for accuracy, and has the evaluation of submissions done in a competitive programming-like setting.”
Improving Factuality and Reasoning in Language Models through Multiagent Debate (2023, unknown): “Existing works have explored how language models can enable applications such as embodied cooperation (Zhang et al., 2023; Mandi et al., 2023; Chen et al., 2023), AI societies (Li et al., 2024), and software engineering (Hong et al., 2023; Wu et al., 2023).”
AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents (2024, background): “The enthusiasm for building such agents is evident by the growing number of computer control agent systems [41, 9, 70, 24, 22, 16] and code repositories [13, 1, 2, 57].”
Empowering Biomedical Discovery with AI Agents (2024, unknown): “The text-based approach lays the groundwork for communication in multi-agent [73, 133] and agent-human scenarios [10, 13].”
τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains (2024, background): “This includes papers on simulating non-player characters (NPCs) in text adventure games [13] multiple agents in human-like societies [15] or specific collaborative tasks [21], and enabling human-in-the-loop interaction for tasks like online shopping [6] or web search [28].”
Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG (2025, unknown): “AG2 [49] (formerly knows as AutoGen [50, 51]) excels in multi-agent collaboration with advanced support for code generation, tool execution, and decision-making.”
The rise and potential of large language model based agents: a survey (2025, unknown): “Additionally, AutoGen [327] is a highly ﬂexible multi-agent development tool that allows users to create customizable agents.”
Promises and challenges of generative artificial intelligence for human learning (2024, unknown): “It classifies cognitive skills into a hierarchy from basic to advanced: remember, understand, apply, analyse, evaluate and create.”
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey (2024, background): “In the field of NLP, Large Language Models (LLMs) have achieved significant advancements across various tasks including text generation [10], [243], translation [239], [61], personalized chat-bots [192], [103], [187], and summarization [212], demonstrating remarkable proficiency.”
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents (2023, unknown): “To facilitate effective decision-making, previous research has investigated the impact of different communication structures among agents (Chan et al., 2023; Zhang et al., 2023b; Wu et al., 2023).”
Why Do Multi-Agent LLM Systems Fail? (2025, unknown): “AG2 (formerly AutoGen) (Wu et al., 2023) is an open-source programming framework for building agents and managing their interactions.”
LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked (2023, background): “The widespread use of LLMs in applications like chat bots and assistants [30] underscores the growing urgency of developing scalable, standardized and straightforward defenses against a diverse range of attacks [34, 20, 12].”
MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning (2023, background): “In essence, the key to LLM-based multi-agent collaboration is the simulation of human activities such as role-playing (Wang et al., 2023d; Hong et al., 2023) and communication (Wu et al., 2023a; Qian et al., 2023; Li et al., 2023b,c).”
Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models (2024, methodology): “Our implementation is based on the AutoGen [52] framework.”
RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation (2024, unknown): “As seen in the table, the GPT series significantly outperforms the LLaMA series in parameter identification, and gpt-4-0125 performs the best.”