Search-R1
A reinforcement learning paradigm for training large language model agents to perform retrieval-augmented reasoning, in which the agent learns to invoke retrieval tools while answering questions and to generate answers incorporating the retrieved results.
Timeline (last 90 days)
The open-source distributed engine Flame has added a Search-R1-style training example for training agents that can search.
The experiment used only a single random seed, the evaluation set contained only 200 questions, and the corpus was built from the context paragraphs of the selected questions, so the scores cannot be directly compared with published Search-R1 benchmark results.
All Facts (2)
The experiment used only a single random seed, the evaluation set contained only 200 questions, and the corpus was built from the context paragraphs of the selected questions, so the scores cannot be directly compared with published Search-R1 benchmark results.
50%UnverifiedThe open-source distributed engine Flame has added a Search-R1-style training example for training agents that can search.
50%