🥳 I'm releasing Rejax, a lightweight library of fully vectorizable RL algorithms! ⚡ Enjoy lightning-fast speed using jax.jit on the training function 🧬Use vmap and pmap on hyperparameters 🔙 Log using flexible callbacks 🌐 Available @ github.com/kerajli/rejax 📸 Take a tour!

🚀

x.com/i/article/1863…

trying to make it really really easy to build LLM RL envs

Today we release DeepSeek-R1T-Chimera, an open weights model adding R1 reasoning to DeepSeek V3-0324 with a novel construction method. In benchmarks, it appears to be as smart as R1 but much faster, using 40% fewer output tokens. The Chimera is a child LLM, using V3s

Introducing GLM-4.5 and GLM-4.5 Air: new flagship models designed to unify frontier reasoning, coding, and agentic capabilities. GLM-4.5: 355B total / 32B active parameters GLM-4.5-Air: 106B total / 12B active parameters API Pricing (per 1M tokens): GLM-4.5: $0.6 Input / $2.2

ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents "To support scalable and robust training, we develop a distributed RL infrastructure capable of orchestrating thousands of parallel virtual desktop environments to accelerate large-scale

Lucky to have collaborated with an amazing team on this work! 🎉🚀😃

🚨Thrilled to share our latest progress on Computer Use Agent, ComputerRL, an end-to-end RL method which achieves 48.1% success rate on OSWorld Benchmark with only 9B open model, beating OpenAI Operator, Claude Sonnet 4.0, and other previous models, state-of-the-art performance.

Someone on rednote said they found bugs in the Open Review system on 11/12/2025 and even sent three emails to the security team, but still haven’t received a reply. Moments like this just reinforce the feeling that the whole world is held together with duct tape. #ICLR2026