THU-KEG/CaRR-DeepDive
Preview • Updated • 393 • 1
CaRR & C-GRPO
Data and models for the paper "Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards".
-
-
THU-KEG/DeepDive-4B-SFT
4B • Updated • 10 -
THU-KEG/DeepDive-4B-C-GRPO
4B • Updated • 3 -
THU-KEG/DeepDive-30B-A3B-SFT
31B • Updated • 4 -
THU-KEG/DeepDive-30B-A3B-C-GRPO
31B • Updated • 1 -
Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards
Paper • 2601.06021 • Published • 48