{"full_name":"PeterGriffinJin/Search-R1","owner":"PeterGriffinJin","name":"Search-R1","shard":"1","url":"https://github.com/PeterGriffinJin/Search-R1","description":"Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL","homepage":"https://arxiv.org/pdf/2503.09516","topics":[],"tag_pages":[],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/48234654?u=055650c97f9d0ff6a19a459f130054b1e0faf3f3&v=4","created_at":"2025-02-28T15:14:47Z","pushed_at":"2025-11-13T21:56:33Z","metrics":{"stars":5579,"forks":503,"watchers":17,"issues":170,"prs":27,"releases":0,"issues_open":29,"issues_closed":141,"prs_open":11,"prs_closed":13,"prs_merged":3,"discussions":0},"growth":{"day":{"stars":0,"forks":-1,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[5572,5574,5575,5576,5577,5579,5579],"forks":[504,504,504,504,504,504,503],"watchers":[null,17,17,17,17,17,17],"issues_open":[null,29,29,29,29,29,29],"prs_open":[null,11,11,11,11,11,11]},"boards":{},"same_owner":[],"issues":[{"number":122,"title":"Self-built data output is abnormal","comments":9,"created_at":"2025-06-25T02:02:54Z"},{"number":88,"title":"Question about GRPO and sample indexing","comments":8,"created_at":"2025-04-25T08:38:05Z"},{"number":153,"title":"Upgrade Search-R1 to support latest vLLM and Verl","comments":5,"created_at":"2025-09-07T09:08:59Z"},{"number":142,"title":"PPO training fails after 50-100 steps usually before it reaches the trainer.save_freq/trainer.test_freq","comments":5,"created_at":"2025-07-25T15:42:46Z"},{"number":155,"title":"Top-k Parameter Set to 3, but 5 Documents Returned for Some Queries During Training","comments":4,"created_at":"2025-09-24T13:30:27Z"},{"number":152,"title":"The training time","comments":4,"created_at":"2025-08-21T11:42:07Z"},{"number":67,"title":"Getting error while running inference","comments":3,"created_at":"2025-04-07T20:13:19Z"},{"number":175,"title":"训练稳定性与信用分配：针对长检索序列实现“跳过检索内容”的 GAE 机制","comments":2,"created_at":"2026-03-07T11:54:04Z"}],"discussions":[],"latest_release":null,"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}