Search-R1-v0.3 Collection RL with outcome reward + format reward. https://arxiv.org/abs/2505.15117 • 12 items • Updated Aug 12, 2025 • 4
Search-R1-v0.2 Collection Exploration with a more stable RL pipeline with outcome-only reward and scaled-up LLMs. https://arxiv.org/abs/2503.09516 • 26 items • Updated Aug 12, 2025 • 6
Search-R1 Collection Preliminary checkpoints with outcome-only RL. • 15 items • Updated Aug 12, 2025 • 18
