AutoGen header graphic showing relationship between User, Commander, Writer, and Safeguard

AutoGen

Open-Source Framework for Agentic AI

aka.ms/autogen (opens in new tab)

autogen@microsoft.com

News & features

Research Forum Episode 5 | Gagan Basal
Articles

Gagan Bansal introduces a transformative update to the AutoGen framework that builds on user feedback and redefines modularity, stability, and flexibility to empower the next generation of agentic AI research and applications.

In the news | TheSequence

AutoGen has undergone significant evolution since its inception, driven by the need for more efficient, flexible, and scalable agentic AI systems. The release of AutoGen v0.4 introduces a fundamental architectural shift, addressing prior inefficiencies and enhancing its capabilities.

The v0.4 update introduces a cohesive AutoGen ecosystem that includes the framework, developer tools, and applications. The framework’s layered architecture clearly defines each layer’s functionality. It supports both first-party and third-party applications and extensions.
Microsoft Research Blog

| Adam Fourney, Ahmed Awadallah, Cheng Tan, Erkang (Eric) Zhu, Friederike Niedtner, Gagan Bansal, Jack Gerrits, Jacob Alber, Peter Chang, Rafah Hosn, Ricky Loynd, Saleema Amershi, Victor Dibia, XiaoYun Zhang, Li Jiang, Ryan Sweet, Leonardo Pinheiro, Mohammad Mazraeh, Gerardo Moreno Zizumbo, Kosta Petan, Aamir Jawaid, Reuben Bond, Diego Colombo, and Hussein Mozannar

Announcing AutoGen 0.4, fully reimagined library for building advanced agentic AI systems, developed to improve code quality and robustness. Its asynchronous, event-driven architecture is designed to support dynamic, scalable workflows.

In the news | Tech Brew

One of the key questions driving Ece Kamar’s research as managing director of Microsoft’s AI Frontiers Lab is how to coordinate networks of these agents—AI systems that can perform autonomous tasks beyond the scope of chatbots. Late last year, her…

In the news | TheSequence

Magentic-One is a new generalist multi-agent system developed by Microsoft Research, designed to handle open-ended tasks based on web and file information across various domains. This essay will examine the architecture of Magentic-One, its capabilities, evaluation results, and potential risks.

Orca-3 blog - abstract wave graphic
Microsoft Research Blog

| Arindam Mitra, Ahmed Awadallah, and Yash Lara

Orca-AgentInstruct, from Microsoft Research, can generate diverse, high-quality synthetic data at scale to post-train and fine-tune base LLMs for expanded capabilities, continual learning, and increased performance.

AutoGen: White icons representing (from left to right) agents (multi), workflow, tasks, and coding on a blue to purple to pink gradient background.
Microsoft Research Blog

| Victor Dibia, Gagan Bansal, Jingya Chen, Suff Syed, Adam Fourney, Erkang (Eric) Zhu, Chi Wang, and Saleema Amershi

AutoGen Studio, built on Microsoft’s flexible open-source AutoGen framework for orchestrating AI agents, provides an intuitive user-friendly interface that enables developers to rapidly build, test, customize, and share multi-agent AI solutions—with little or no coding.

Research Focus: June 10, 2024
Microsoft Research Blog

In this issue: RELEVANCE automatically evaluates creative LLM responses; Recyclable vitrimer-based printed circuit boards; Lean Attention: Hardware-aware scalable attention mechanism; WaveCoder: a fine-tuned code LLM; New AutoGen training course.

In the news | Wired

I’ve been playing this week with AutoGen, an open source software framework for AI agent collaboration developed by researchers at Microsoft and academics at Pennsylvania State University, the University of Washington, and Xidian University in China. The software taps OpenAI’s…