:fire: May 24, 2024: Foundation Capital published an article on [Forbes: The Promise of Multi-Agent AI](https://www.forbes.com/sites/joannechen/2024/05/24/the-promise-of-multi-agent-ai/?sh=2c1e4f454d97) and a video [AI in the Real World Episode 2: Exploring Multi-Agent AI and AutoGen with Chi Wang](https://www.youtube.com/watch?v=RLwyXRVvlNk).
:fire: May 13, 2024: [The Economist](https://www.economist.com/science-and-technology/2024/05/13/todays-ai-models-are-impressive-teams-of-them-will-be-formidable) published an article about multi-agent systems (MAS) following a January 2024 interview with [Chi Wang](https://github.com/sonichi).
:fire: May 11, 2024: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://openreview.net/pdf?id=uAjxFFing2) received the best paper award at the [ICLR 2024 LLM Agents Workshop](https://llmagents.github.io/).
:fire: Apr 17, 2024: Andrew Ng cited AutoGen in [The Batch newsletter](https://www.deeplearning.ai/the-batch/issue-245/) and [What's next for AI agentic workflows](https://youtu.be/sal78ACtGTc?si=JduUzN_1kDnMq0vF) at Sequoia Capital's AI Ascent (Mar 26).
:fire: Mar 3, 2024: What's new in AutoGen? 📰[Blog](https://microsoft.github.io/autogen/blog/2024/03/03/AutoGen-Update); 📺[Youtube](https://www.youtube.com/watch?v=j_mtwQiaLGU).
:fire: Mar 1, 2024: the first AutoGen multi-agent experiment on the challenging [GAIA](https://huggingface.co/spaces/gaia-benchmark/leaderboard) benchmark achieved the No. 1 accuracy in all the three levels.
:tada: Dec 31, 2023: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https://arxiv.org/abs/2308.08155) is selected by [TheSequence: My Five Favorite AI Papers of 2023](https://thesequence.substack.com/p/my-five-favorite-ai-papers-of-2023).
<!-- :fire: Nov 24: pyautogen [v0.2](https://github.com/microsoft/autogen/releases/tag/v0.2.0) is released with many updates and new features compared to v0.1.1. It switches to using openai-python v1. Please read the [migration guide](https://microsoft.github.io/autogen/docs/Installation#python). -->
<!-- :fire: Nov 11: OpenAI's Assistants are available in AutoGen and interoperatable with other AutoGen agents! Checkout our [blogpost](https://microsoft.github.io/autogen/blog/2023/11/13/OAI-assistants) for details and examples. -->
:tada: Nov 8, 2023: AutoGen is selected into [Open100: Top 100 Open Source achievements](https://www.benchcouncil.org/evaluation/opencs/annual.html) 35 days after spinoff from [FLAML](https://github.com/microsoft/FLAML).
:fire: [autogen](https://microsoft.github.io/autogen/) is released with support for ChatGPT and GPT-4, based on [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://arxiv.org/abs/2303.04673).
AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. AutoGen agents are customizable, conversable, and seamlessly allow human participation. They can operate in various modes that employ combinations of LLMs, human inputs, and tools.
- AutoGen enables building next-gen LLM applications based on [multi-agent conversations](https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat) with minimal effort. It simplifies the orchestration, automation, and optimization of a complex LLM workflow. It maximizes the performance of LLM models and overcomes their weaknesses.
- It supports [diverse conversation patterns](https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat#supporting-diverse-conversation-patterns) for complex workflows. With customizable and conversable agents, developers can use AutoGen to build a wide range of conversation patterns concerning conversation autonomy,
- It provides a collection of working systems with different complexities. These systems span a [wide range of applications](https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat#diverse-applications-implemented-with-autogen) from various domains and complexities. This demonstrates how AutoGen can easily support diverse conversation patterns.
- AutoGen provides [enhanced LLM inference](https://microsoft.github.io/autogen/docs/Use-Cases/enhanced_inference#api-unification). It offers utilities like API unification and caching, and advanced usage patterns, such as error handling, multi-config inference, context programming, etc.
AutoGen is powered by collaborative [research studies](https://microsoft.github.io/autogen/docs/Research) from Microsoft, Penn State University, and the University of Washington.
*NOTE*: OAI_CONFIG_LIST_sample lists GPT-4 as the default model, as this represents our current recommendation, and is known to work well with AutoGen. If you use a model other than GPT-4, you may need to revise various system prompts (especially if using weaker models like GPT-3.5-turbo). Moreover, if you use models other than those hosted by OpenAI or Azure, you may incur additional risks related to alignment and safety. Proceed with caution if updating this default.
Find detailed instructions for users [here](https://microsoft.github.io/autogen/docs/installation/Docker#step-1-install-docker), and for developers [here](https://microsoft.github.io/autogen/docs/Contribute#docker-for-development).
<!-- For example, use the following to install the dependencies needed by the [`blendsearch`](https://microsoft.github.io/FLAML/docs/Use-Cases/Tune-User-Defined-Function#blendsearch-economical-hyperparameter-optimization-with-blended-search-strategy) option.
Even if you are installing and running AutoGen locally outside of docker, the recommendation and default behavior of agents is to perform [code execution](https://microsoft.github.io/autogen/docs/FAQ/#code-execution) in docker. Find more instructions and how to change the default behaviour [here](https://microsoft.github.io/autogen/docs/Installation#code-execution-with-docker-(default)).
Autogen enables the next-gen LLM applications with a generic [multi-agent conversation](https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat) framework. It offers customizable and conversable agents that integrate LLMs, tools, and humans.
By automating chat among multiple capable agents, one can easily make them collectively perform tasks autonomously or with human feedback, including tasks that require using tools via code.
Features of this use case include:
- **Multi-agent conversations**: AutoGen agents can communicate with each other to solve tasks. This allows for more complex and sophisticated applications than would be possible with a single LLM.
- **Customization**: AutoGen agents can be customized to meet the specific needs of an application. This includes the ability to choose the LLMs to use, the types of human input to allow, and the tools to employ.
- **Human participation**: AutoGen seamlessly allows human participation. This means that humans can provide input and feedback to the agents as needed.
For [example](https://github.com/microsoft/autogen/blob/main/test/twoagent.py),
user_proxy = UserProxyAgent("user_proxy", code_execution_config={"work_dir": "coding", "use_docker": False}) # IMPORTANT: set to True to run code in docker, recommended
Alternatively, the [sample code](https://github.com/microsoft/autogen/blob/main/samples/simple_chat.py) here allows a user to chat with an AutoGen agent in ChatGPT style.
Autogen also helps maximize the utility out of the expensive LLMs such as ChatGPT and GPT-4. It offers [enhanced LLM inference](https://microsoft.github.io/autogen/docs/Use-Cases/enhanced_inference#api-unification) with powerful functionalities like caching, error handling, multi-config inference and templating.
<!-- For example, you can optimize generations by LLM with your own tuning data, success metrics, and budgets.
- [Research](https://microsoft.github.io/autogen/docs/Research), [blogposts](https://microsoft.github.io/autogen/blog) around AutoGen, and [Transparency FAQs](https://github.com/microsoft/autogen/blob/main/TRANSPARENCY_FAQS.md)
author={Qingyun Wu and Gagan Bansal and Jieyu Zhang and Yiran Wu and Beibin Li and Erkang Zhu and Li Jiang and Xiaoyun Zhang and Shaokun Zhang and Jiale Liu and Ahmed Hassan Awadallah and Ryen W White and Doug Burger and Chi Wang},
title={An Empirical Study on Challenging Math Problem Solving with GPT-4},
author={Yiran Wu and Feiran Jia and Shaokun Zhang and Hangyu Li and Erkang Zhu and Yue Wang and Yin Tat Lee and Richard Peng and Qingyun Wu and Chi Wang},
If you are new to GitHub, [here](https://opensource.guide/how-to-contribute/#how-to-submit-a-contribution) is a detailed help source on getting involved with development on GitHub.
Microsoft and any contributors grant you a license to the Microsoft documentation and other content
in this repository under the [Creative Commons Attribution 4.0 International Public License](https://creativecommons.org/licenses/by/4.0/legalcode),
see the [LICENSE](LICENSE) file, and grant you a license to any code in the repository under the [MIT License](https://opensource.org/licenses/MIT), see the
[LICENSE-CODE](LICENSE-CODE) file.
Microsoft, Windows, Microsoft Azure, and/or other Microsoft products and services referenced in the documentation
may be either trademarks or registered trademarks of Microsoft in the United States and/or other countries.
The licenses for this project do not grant you rights to use any Microsoft names, logos, or trademarks.
Microsoft's general trademark guidelines can be found at http://go.microsoft.com/fwlink/?LinkID=254653.
Privacy information can be found at https://privacy.microsoft.com/en-us/
Microsoft and any contributors reserve all other rights, whether under their respective copyrights, patents,
or trademarks, whether by implication, estoppel, or otherwise.
