DR Tulu is now accepted for an oral presentation at #ICML2026 🙏 Updated paper: arxiv.org/abs/2511.19399 📥We added more ablations including using Qwen3-8B as the rubric generator&judge, showing evolving rubrics work with a weak model too; spurious rewards sanity check, etc.

Our team will present DR Tulu and Spurious Rewards at #ICML2026! Sadly, I'm not attending in person. Please come and chat with my superstar coauthors! DR Tulu: - Wed. July 8 10:15-10:30 AM KST, Hall B2 (Oral presentation) - Wed. July 8 2:30-4:15 PM KST, Hall A #1800 (Poster)

Great work! Still rememberer I was so shocked when Katelyn asked me to guess the median number of reviews in human studies and she told me it was 3 & they mostly came from the paper authors 🌚

Amazing work by

and @yinn_oscar on an open-source training recipe for terminal agents. The data and RL details are well worth digging into. It’s surprisingly exciting how much is still left to figure out😀

Claude Code on GitHub that self-evolves. Leave your laptop on your desk 😌Check out

! Meme: when a singer has to debug on the go.