RL ReSearch

non-profit

AI & ML interests

None defined yet.

Papers

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

View all Papers

Collections 1

models 7

rl-research/DR-Tulu-8B-results

Updated Mar 26 • 1

rl-research/DR-Tulu-8B-Step-1900-results

rl-research/DR-Tulu-8B-Step-1900

Text Generation • 8B • Updated Mar 26 • 8

rl-research/DR-Tulu-No-RLER-8B

Text Generation • 8B • Updated Feb 24 • 6

rl-research/DR-Tulu-8B

Text Generation • 8B • Updated Feb 24 • 2.35k • • 75

rl-research/dr-tulu-shortform-rl-400step

8B • Updated Jan 2 • 5

rl-research/DR-Tulu-SFT-8B

Text Generation • 8B • Updated Nov 29, 2025 • 88 • • 5

datasets 11

rl-research/eval_outputs

Viewer • Updated Mar 20 • 836 • 65

rl-research/dr-tulu-eval-data

Updated Mar 6 • 62

rl-research/multimodal-rewardbench-2

Viewer • Updated Dec 20, 2025 • 4k • 353 • 4

rl-research/dsqa

Viewer • Updated Dec 18, 2025 • 900 • 30.3k

rl-research/dr-tulu-rl-data

Viewer • Updated Nov 25, 2025 • 4.88k • 221 • 14

rl-research/dr-tulu-sft-data

Viewer • Updated Nov 25, 2025 • 13.1k • 245 • 29

rl-research/genetic_diseases_qa

Preview • Updated Nov 24, 2025 • 36

rl-research/deep_research_bench_eval

Viewer • Updated Nov 23, 2025 • 100 • 335

rl-research/webwalker_test

Viewer • Updated Nov 23, 2025 • 680 • 95

rl-research/researchqa_official_subset_ids

Viewer • Updated Nov 23, 2025 • 776 • 100

View 11 datasets