🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

SIGIR VF Presents "AutoGen: A Programming Framework for Agentic AI" Join us to learn how to build LLM-based Applications 👉REGISTER: forms.gle/1Mw8CDQ3BX63Cz… (Free of Charge) Negar Arabzadeh Suzan Verberne 🤹‍♀️ ACM SIGIR SIGIR 2025 Bhaskar Mitra | ভাস্কর মিত্র L. Dietz @[email protected] @[email protected] Ryen White AutoGen Chi Wang

Paper accepted to Conference on Language Modeling! If you don't know CoLM, it's Neurips-level, but the 𝘧𝘪𝘳𝘴𝘵 𝘦𝘷𝘦𝘳 𝘤𝘰𝘯𝘧𝘦𝘳𝘦𝘯𝘤𝘦 𝘧𝘰𝘳 𝘓𝘓𝘔𝘴. Wild. Publishing papers while building a 𝘀𝘁𝗮𝗿𝘁𝘂𝗽 with 𝟭𝗠+ users is never easy. We developed 𝗦𝘁𝗮𝘁𝗲𝗙𝗹𝗼𝘄, a framework to

🎉🎉Thrilled to share the acceptance of both AutoGen and StateFlow (microsoft.github.io/autogen/blog/2…) to the very first Conference on Language Modeling with strong ratings! The past few months have been crazy with the explosive growth of AutoGen! 🚀🚀The project has attracted 28.3k stars and a vibrant

🎉 Diffusion-style annealing + sampling-based MPC can surpass RL, and seamlessly adapt to task parameters, all 𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴-𝗳𝗿𝗲𝗲! We open sourced DIAL-MPC, the first training-free method for whole-body torque control using full-order dynamics 🧵 lecar-lab.github.io/dial-mpc/

If you are at #COLM2024 Conference on Language Modeling, come and learn more about StateFlow in the poster session tmr afternoon!

"Only-IF: Revealing the Decisive Effect of Instruction Diversity on Generalization" arxiv.org/pdf/2410.04717 We isolated 'instruction-following' ability (apart from complex reasoning like math) and designed various controlled experiments to show that -

best conference experience small but sweet < 1,000 attendences vs 10,000 at neurips engaging easy to spot people when you are looking for someone to talk to diverse but very focused on llm really feel appreciated for organizers Sasha Rush Yoav Artzi Conference on Language Modeling and my co-authors

Visiting and giving a talk at UChicago next week! And planning an #Autogen local meetup nearby on Wednesday, 10/30 - Join fellow AutoGen enthusiasts 🤖🤖 if you are around! Details in our Discord's `geo-chicago` channel discord.com/channels/11530…!

Thrilled to be sharing the latest developments in the AI agent spaces through the lens of #AutoGen at MLOps World next week. MLOps World is a fantastic platform for AI/ML innovators and practitioners to exchange notes. I fondly recall the session we (together with Chi Wang )

🚀 Big News: AutoGen is Now AG2! 🚀 We’re evolving! With support from the #OSS community, AutoGen is becoming #AG2, a new home for next-gen agentic #AI. Same mission, bigger goals. → Repo: github.com/ag2ai/ag2 ⭐️ → Docs: ag2ai.github.io/ag2 → Same Discord:

🚀 HUGE: AG2 v0.4 just dropped two game-changing features! Meet CaptainAgent: Your ultimate AI architect that auto-builds perfect agent teams based on your tasks. PLUS: SwarmAgent brings OpenAI Swarm-inspired collab with shared context & seamless handoffs! 20K+ builders

🎉 CaptainAgent & SwarmAgent have landed in AG2 v0.4! Two powerful ways to orchestrate your agentic workflows: - CaptainAgent: Your Ultimate AI Team Builder! - SwarmAgent: Close collaboration, distributed execution! Level up your AI agents today with AG2! 🚀

💡 A fantastic resource for mastering advanced AI agent development! Must-read for anyone diving into AI agents!

🚀 Exciting news! FastAgency (github.com/ag2ai/fastagen…) & FastStream (github.com/ag2ai/faststre…) are now part of the AG2 OSS family! 🔥 FastAgency: Deploy multi-agent workflows with a unified programming interface ⚡ FastStream: Build distributed apps supporting Kafka, RabbitMQ,

❄️Introducing Absolute Zero Reasoner: Our reasoner learns to both propose tasks that maximize learnability and improve reasoning by solving them, entirely through self-play—with no external data! It overall outperforms other "zero" models in math & coding domains. 🧵 1/

Thanks for sharing!

The GAIA game is over, and Alita is the final answer. Alita takes the top spot in GAIA, outperforming OpenAI Deep Research and Manus. Many general-purpose agents rely heavily on large-scale, manually predefined tools and workflows. However, we believe that for general AI

Sigh, it's a bit of a mess. Let me just give you guys the full nuance in one stream of consciousness since I think we'll continue to get partial interpretations that confuse everyone. All the little things I post need to always be put together in one place. First, I have long