Super excited to share 💪🧠Reasoning Gym! 🧵 We provide over 100 data generators and verifiers spanning several domains (algebra, arithmetic, code, geometry, logic, games) for training the next generation of reasoning models. In essence, we can generate an infinite amount of

This takes me back to 2023 building Open Assistant. Too many users for the limited GPUs we had for inference, so one idea was to prioritise users who provided more feedback data. Granular feedback from highly heterogenous human raters is very messy, though.

Congrats to Prime on the release of their new open reasoning dataset. Nice to see Reasoning Gym tasks used extensively in SYNTHETIC-2!

Stop overfitting to GSM8K! Reasoning Gym - 100+ RL envs for LLM RL - got accepted to NeurIPS as Spotlight! Frontier LLMs still struggle with many hard env configs. arxiv.org/abs/2505.24760 github.com/open-thought/r…

I'm late to this but a couple of weeks ago Reasoning Gym was accepted as a spotlight at NeurIPS ⭐️ I'll be attending, in San Diego from 2nd December until the 7th - if anyone wants to chat, reach out!