DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
Paper
• 2511.19399 • Published
• 62
DR Tulu
Models and data associated with DR Tulu, http://allenai-web/papers/drtulu
Note Our paper!
rl-research/DR-Tulu-8B
Text Generation • 8B • Updated • 1.47k • 71Note Final RLER-trained model.
rl-research/DR-Tulu-SFT-8B
Text Generation • 8B • Updated • 250 • 5Note SFT model.
rl-research/dr-tulu-sft-data
Viewer • Updated • 13.1k • 218 • 26Note Data used for SFT training.
rl-research/dr-tulu-rl-data
Viewer • Updated • 4.88k • 278 • 12Note Data used for RL training.
rl-research/DR-Tulu-No-RLER-8B
Text Generation • 8B • UpdatedNote Ablation model, trained with RL without RLER.