[Update] Our team will be accepting PhD Internship applications until **January 5th, 2024**. Please apply by then if you're interested in working with us! See👇for details.

New blog by Adam Fourney (hci.social/@adam) and Qingyun Wu on measurement tools for complex multi agent workflows in AutoGen. AutoGenBench is a command line tool on pypi which handles downloading, configuring, running, and reporting supported benchmarks in AutoGen.➡️microsoft.github.io/autogen/blog/2…

Join us at #MicrosoftResearch AI Frontiers! 👇

#internopportunity, summer 2024 … if you are a HCI PhD student interested in helping define the future of tools for creating multi-agent applications (AutoGen, AutoGen Studio, AutoGen), and a builder, please reach out to me, Gagan Bansal or Adam Fourney (hci.social/@adam) (DM or email). A

phi-3 is here, and it's ... good :-). I made a quick short demo to give you a feel of what phi-3-mini (3.8B) can do. Stay tuned for the open weights release and more announcements tomorrow morning! (And ofc this wouldn't be complete without the usual table of benchmarks!)

Researchers at Microsoft emphasize the importance of globally equitable AI. Join us at Research Forum on June 4 to learn more about data representation, the latest foundational advances, and how inclusive AI creates impact. Register now.

Don't miss Adam Fourney's talk on June 4 at Microsoft Research Forum, where he will discuss the effectiveness of using multiple agents, working together, to complete complex multi-step tasks. Register now. msft.it/6010YkH4E

To learn more about building reliable agents for solving complex tasks with #AutoGen signup for this Microsoft Research forum talk!

Over the last few months, I have been working on a low code developer tool (AutoGen Studio) to enable rapid prototyping of multi-agent systems using AutoGen. Really excited to see the work highlighted on the Microsoft Microsoft Research blog today! In the blog, we cover tasks

+Victor Dibia, who led this work, and Jingya Chen Suff Syed who have been instrumental in its design

As part of the Microsoft Research forum (x.com/MSFTResearch/s… ), I'm running a panel on multimodal models (x.com/msftresearch/s… ) which seems like a fun topic. Register/join if that's your jam :-)

This new paper from Massachusetts Institute of Technology (MIT) uses multiple #AutoGen agents to generate, refine, and validate research hypothesis! SciAgents: Automating Scientific Discovery Through Multi-Agent Intelligent Graph Reasoning by Ghafarollahi & Markus J. Buehler "We present SciAgents, an approach that

Excited to announce the release of Eureka, an open-source framework for evaluating and understanding large foundation models! 🌟 Eureka offers: 🔍In-depth analysis of 12 cutting-edge models 🧠 Multimodal & language capability testing beyond single-score reporting and rankings 📈

🚀#AI advances are accelerating, with new models emerging regularly. Benchmark scores only reveal so much. For #HumanCenteredAI, we must ask: How will this model work in my app and for my users? Eureka standardizes LLM evaluation for deeper insights beyond single-score metrics👇