Ankush Garg

LLMs@ ReflectionAI,
prev: Meta/MSL, Gemini/GDM/Google Brain,
UMass Amherst

[Ankush Garg @agbgarg]

@achowdhery @alexpolozov @tolgab0 @gamaleldinfe @_samwiseman @Jinwu76 @GlabRed @jjjhadid @official_j3rck @Selva_5597 @_sdbuchanan Congratulations and thanks for leading the foundational work on pretraining!

[Ankush Garg @agbgarg]

@alexpolozov Thanks @alexpolozov for your leadership!! Congrats to the whole team!

[Ankush Garg @agbgarg]

We built our first model!!
It's been fun, challenging, exciting and everything in between scaling pretraining and mid training science and infrastructure from scratch.
Shoutout to @_ghorbani @mojan_jp @alexpolozov @MishaLaskin @real_ioannis for inspiring leadership!

[Reflection @reflection_ai]

Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active.

- Frontier reasoning efficiency
- Advances the Western open frontier on coding & agentic tasks
- Trained end-to-end from scratch

Full weights release this month.

Learn more about Beam: https://t.co/c3Qx2cpM8G

[Ankush Garg @agbgarg]

Super fun to work with you again after years! Your knack for clean science and experimentation has always been an inspiration for me. Cheers!

[Behrooz Ghorbani @_ghorbani]

Today, we’re introducing Beam, @reflection_ai's first model.

We started the high-compute RL team in February. Looking back at these past few months, it’s remarkable how far we’ve come.

Making RL work at this scale took careful science, scalable infrastructure, and a strong foundation from mid-training. Seeing that work come together to keep learning stable as we pushed the scale and complexity of the run has been incredibly rewarding.

What has made this especially meaningful is the people: their commitment and curiosity, the way they supported one another through difficult stretches, and the joy of figuring things out together.

To everyone who helped bring Beam to life, across RL science, infrastructure, mid-training, pretraining, and our close collaborators throughout Reflection: thank you. There is so much of your hard work and care in this model.

Building and leading this team has been an honor and one of the most rewarding experiences of my career. I’ve learned so much from the people around me, and I’m proud of what we’ve built together.

@MishaLaskin and @real_ioannis, thank you for your trust and support throughout this journey.

This is our first model, and there’s so much more ahead. I’m excited to share Beam with the community, learn from your feedback, and continue building better models together.

[Ankush Garg @agbgarg]

So glad to work closely with you; I learn so much from your enthusiasm, knowledge and bias for speed. Congrats to the whole team!

[Mojan Javaheripi @mojan_jp]

So happy to finally share what we have been working on @reflection_ai . The speed at which the team is building and pushing for the frontier is insane. Cheers to more to come! More on our tech details soon :)

[Behrooz Ghorbani @_ghorbani]

Proud to share that Reflection is partnering with Shinsegae Group to build a 250MW AI factory for Korea’s sovereign AI 🇰🇷

Excited to keep pushing the frontiers of RL, reasoning, and open models with this team!

https://t.co/1e09vRFLnX

[Ankush Garg @agbgarg]

@_arohan_ @AnthropicAI Congrats Rohan! Will miss having you around. Best wishes ahead :)

[Ankush Garg @agbgarg]

@choudharydhruv It is an honor to be collaborating with you and this stellar team :)

[Ankush Garg @agbgarg]

@_arohan_ @AIatMeta Welcome to the team Rohan!