Amsterdam, The Netherlands
Joined March 2012
- Tweets14
- Following28
- Followers36
- Likes42
Anton Shevtsov retweeted
🚀 SWE-rebench V2.1 RL is out: 13,337 free RL environments for coding agents (20 languages, Harbor format)!
🔧 Fixed tasks, envs, and graders → fast, reliable rollouts.
Doing RL post-training or research? DM or reply. We can share data and RL envs early for free, so we can make them better for open source!
🙏 Please RT or share with anyone who might need free RL envs!
Anton Shevtsov retweeted
LMs can play chess, but they can't really explain their moves well (chess engines can't at all). Our new BinProp scaffold tackles this, and nearly triples LMs’ score on our chess-explanation benchmark. It works on other games too!
Try it on your own games on our site-🧵👇
Anton Shevtsov retweeted
We evaluated GPT 5.4 on AlgoTune: for the first time an @OpenAI model is worse than its predecessor. Some analysis:
In graph_laplacian, GPT-5.2's approach is: build the sparse matrix once, call SciPy’s Laplacian routine, and return the sparse result directly.
(cont.)🧵
Anton Shevtsov retweeted
📟 Meet SWE-rebench-V2: the largest open, multilingual, executable dataset for training code agents!
We at Nebius AI R&D are releasing the biggest open dataset of RL environments for training coding agents. We built an automated pipeline to extract real-world tasks at scale, and now we are sharing everything with the community. This release is designed for large-scale RL training.
What’s inside:
> 32,000+ executable tasks — every task is based on a real-world issue and comes with a pre-built Docker env.
> 20 programming languages — moving beyond Python-only datasets (including less-represented ones like Lua, Clojure, etc.).
> 120,000+ extra tasks derived from real pull requests.
> High quality — tasks are filtered and labeled using an LLM ensemble. They are also enriched with metadata and tested interfaces to ensure solvability.
We are also dropping a technical report with all the details on our extraction pipeline and model evaluations.
📄 Paper and dataset: huggingface.co/papers/2602.2…
👾 Discord (we are online there for any feedback/issues): discord.gg/wXYmWpMu
We are open to research collaborations — feel free to reach out!
🔁 If you find this useful, please help us spread the word by sharing
Anton Shevtsov retweeted
Running MCTS in stateful environments, rolling back faulty actions, branching for exploration, reverting a series of steps once you hit a dead end – all of this kept coming up in our SWE-agent research for the past year. And it required a lot of complex tooling, especially for Docker containers where actions aren't easily revertible.
Today our R&D team is releasing contree.dev – a sandbox we built to solve exactly this. The core idea is that ConTree snapshots the container filesystem state after each command, so all of the above becomes straightforward to implement.
If you're working on SWE-agent research, you might find it especially useful. It goes with 7k+ SWE environments ready to launch, as well as mini-SWE-agent integration. It's early access right now and we have some keys available. DM me if you're interested, feedback is very much appreciated.
Anton Shevtsov retweeted
Our own SWE-rebench just became the #1 most downloaded dataset on @HuggingFace 🥇
SWE-rebench is a dataset and benchmark for code agents based on LLMs, developed by our AI R&D team. It has been downloaded more than 3.9M times — 3.1M in the last month. 1/4
Anton Shevtsov retweeted
Spirit of open-source is in the air thanks to DeepSeek! And today we are happy to release kvax, our implementation of flash attention for jax! It is very fast and has some advanced features such as context parallelism support that might not be easy to come by. Details ⬇️
Anton Shevtsov retweeted
We release world’s first datasets for training software engineering agents🔥
More specifically, our AI R&D team uploaded two datasets to @HuggingFace: one with 6,411 Issue-PR pairs, and the other with 80,036 agent trajectories. Learn more on our blog: eu1.hubs.ly/H0fwMB00
