SKU RLE-1402 · Sold by External
Search-R1
Product specifications
| SKU | RLE-1402 |
|---|---|
| Data type | RL environments |
| Volume | retrieval-augmented QA training framework |
| Size on disk | Not published by source |
| Format | Python (built on veRL; installed from source via conda/pip) |
| Access model | PUBLIC LICENSE |
| Pricing | Free · open-source license |
| Quality score | — |
| License | Apache-2.0 |
Search-R1 is an RL framework (built on veRL) for training reasoning-and-searching LLMs that emit <search>query</search>, receive retrieved <information>, and produce a final <answer>. The search engine (local sparse/dense retrievers over a Wikipedia corpus, or online search) acts as the environment; it uses retrieved-token masking for stable RL and an outcome-based reward. Supports PPO, GRPO, and REINFORCE across Llama3 and Qwen2.5 models; trained and evaluated across 7 QA benchmarks. It is a training framework rather than a fixed-count environment catalog.