Egor Bogomolov

Leading ML Division @ JetBrains Research
ML on source code, fancy stuff to make SE better.

[Nikita Pavlichenko @nv_pavlichenko]

Today we're releasing Mellum2: our first "serious" LLM.

This is a 12B A2.5B MoE LLM pre-trained on ~11T tokens and post-trained with RLVR.
I'm proud to be leading the team that was working on it for the last 6 months.

We release base/SFT/RL checkpoints along with a tech report

[JetBrains @jetbrains]

RL training and coding-agent experiments not scaling locally? IdeGYM fixes that – and it's now open source. https://t.co/4hrxkNH2lp

[Egor Bogomolov @egor_bb]

A pleasure to see our work posted by AK 😊
📉Issue: GRPO hurts generation diversity and pass@k/max@k do not grow as well as pass@1
📈Solution: we estimate gradients for both on- and off-policy cases to optimize max@k directly, and it shows better yields in code generation tasks (measured as the ratio of passed tests)

[AK @_akhaliq]

The Best of N Worlds

Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation

[Egor Bogomolov @egor_bb]

Interesting @NeurIPSConf experience: a weird mix of likely the most positive review I’ve received and an overriding PC reject on top of it 🤔

[IDE Workshop @IDEworkshop]

The 3rd IDE Workshop @ICSEconf 2026 is scheduled for Saturday, April 18th!

Please submit your short papers and extended abstracts on anything IDE-related: plugins, studies, refactorings, environments, AI in IDE, etc.!

All information here: https://t.co/PNeeFLI8Sz

🏝️🏝️🏝️

[andrew zakonov @andrewzakonov]

JetBrains Junie is live — for everyone!
single AI subscription.
pro tier included with all products pack and dotultimate.

[Egor Bogomolov @egor_bb]

@InceptionAILabs Is there an API to access the model? I would be happy to run it on some coding benchmarks, but I have not find any points to the API yet.

[Egor Bogomolov @egor_bb]

@john_lam @headinthebox Hi, author here. For code generation task we give model an instruction in natural language and access to the library. The reference code is only used for evaluation to compute metrics

[Timofey Bryksin @timofeybryksin]

Interested in impacting millions of developers with your ML research? We at JetBrains Research are hiring! https://t.co/SnTUOjPTRK

[Egor Bogomolov @egor_bb]

🤝 Great thanks to @saridormi, Timur Galimzyanov, Evgeniy Glukhov, Anton Shapkin, @tigina_maria, @areyde, Alexander Kovrigin, @avandeursen, @MalihehIzadi, and @timofeybryksin for a fantastic work!

Please submit to our leaderboard, and we will see you in Long Code Arena! 🏟️

[Egor Bogomolov @egor_bb]

Models' contexts are getting so big that they can (and often should!) include an entire repository, while we are still evaluating them on methods and files. That's why we created Long Code Arena.

Pre-print: https://t.co/q1HTcvnjwe
Datasets: https://t.co/UszSNix6J1

Details in🧵!

[Egor Bogomolov @egor_bb]

🗂️ Module summarization — based on the module’s or project’s source code and a short description of the desired documentation, the model should generate it, testing its abilities in large comprehensive natural language texts. This benchmark includes custom LLM-based evaluation.