![Hussein Mozannar Profile](https://pbs.twimg.com/profile_images/1668024174655225858/1QZUkC-5_x96.jpg)
Hussein Mozannar
@HsseinMzannar
Followers
2K
Following
1K
Statuses
266
AI Researcher @MSFTResearch | PhD @mitidss | 🇱🇧
Joined December 2011
RT @bansalg_: Excited to represent the AutoGen team at this year's Research Forum! Sign up for my talk below! This is joint work with many…
0
7
0
@giangnguyen2412 there is a limit unfortunately for o1, but not for 4o. Over time, I find you get good at figuring out where o1 is more useful than 4o, so you can get better at budgeting your queries
0
0
2
I have been recently involved in rebuilding AutoGen, and the framework now makes it easy to do a lot of agentic research we're doing at MSR from web agents, synthetic data generation, LLM-orchestration and agent UI. Upcoming updates will help support static workflows and memory.
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. Learn more:
0
6
44
RT @BehlHarkirat: Today we release Phi-4 🚀 A small yet mighty model which performs at par with GPT-4o-mini and recently released Llama-3.3…
0
252
0
RT @SaleemaAmershi: 🌟Excited to be at #NeurIPS this year! 🎉 If you're into #AutoGen🤖or looking for full-time/internship roles at #MSRAIFron…
0
4
0
Grateful to have the chance to present Magentic-One at @SemanticScholar, watch for an overview of our latest work led by @adamfourney @bansalg_ and our team at AI Frontiers
Checkout this new talk about MagenticOne and AutoGen by @HsseinMzannar at @allen_ai @SemanticScholar Link:
0
3
18
RT @bansalg_: ☀️Excited to share our new paper! Generative AI agents are powerful but complex—how do we design them for transparency and h…
0
72
0
RT @pyautogen: To our collaborators & community: We’ve seen questions about AutoGen forks/clones vs. the official project. Here's a summar…
0
24
0
@swyx @MSFTResearch @pyautogen @AutogenAI We'll soon release more details about the upcoming version of AutoGen, for now the FAQ on the autogen readme has some info, key among the changes are asynchronous messaging, distributed agents, a more modular codebase/extensions
1
0
1
@swyx @MSFTResearch @pyautogen AutoGen is our agent framework, Magentic-One is a particular multi agent team implemented with AutoGen. We rebuilt AutoGen to support this use case and much more.
1
0
2
RT @SaleemaAmershi: In some better news… We're hiring! 📢 Join us in creating reliable, useful, and safe #AI #agents and systems.🤖 If you🩷w…
0
28
0
RT @pyautogen: 🧵#AutoGen Magentic-One is exhibits strong generalist performance, you can use it for so many open-ended, every day tasks. He…
0
15
0
RT @bansalg_: Excited to finally release Magentic-One! The thing I love about this multi-agent team is that the same implementation achiev…
0
2
0
RT @pyautogen: 📢Introducing Magentic-One, a generalist 5-agent multi-agent system for solving open-ended web- and file-based tasks. 🤖🤖🤖🤖🤖…
0
114
0