# PeterGriffinJin/Search-R1

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Repository: https://github.com/PeterGriffinJin/Search-R1
Canonical: https://ross.abutalabs.com/products/search-r1
Homepage: https://arxiv.org/pdf/2503.09516
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-11-13T21:56:33+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 52, release rhythm 35, longevity 39
- inputs: {"age_days": 551, "days_push": 293, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5328, forks 483 (observed 2026-08-28T04:09:15.678215+00:00)

## What it is
Search-R1 is an open-source reinforcement learning framework for training LLMs that interleave reasoning with search engine calls, built on top of veRL. It supports multiple RL methods (PPO, GRPO, REINFORCE), LLMs (Llama, Qwen), and search backends (local sparse/dense retrievers and online engines).

## Use cases
- train an LLM to reason and call a search engine with reinforcement learning
- build an open-source alternative to OpenAI DeepResearch
- fine-tune Qwen or Llama models with PPO or GRPO for tool-augmented reasoning
- research RL training for interleaved reasoning and retrieval
- train models to interleave chain-of-thought with retrieval calls

## When to choose
- you want to RL-train LLMs to interleave reasoning with search engine calls
- you need an open-source pipeline replicating DeepSeek-R1-style training with retrieval
- you are doing research on tool-augmented LLM reasoning

## When to avoid
- you only need inference-time RAG without training
- you lack GPU resources for RL fine-tuning
- you need a production search agent rather than a research training framework

## Facets
- artifact type: framework
- maturity: active
- function: llm-training, reinforcement-learning, rag, agent-framework, machine-learning
- domain: large-language-models, reinforcement-learning, machine-learning
- platform: python
- tags: rl-training, tool-calling, search-engine-calling, verl, ppo, grpo, deep-research, llm-reasoning, retrieval-augmented-generation, ai-agents, gpu, linux, docker

## Member repositories
- PeterGriffinJin/Search-R1 (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:15.678215+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:58:54.019614+00:00, confidence not recorded.
  - readme: https://github.com/PeterGriffinJin/Search-R1 (fetched 2026-08-28T04:09:15.678215+00:00, sha 7731049c21ea)
- Data as of 2026-08-30T08:39:29.467469+00:00.