RUCAIBox/R1-Searcher
R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
No description.
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
Simple RL training for reasoning
[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)
[ACL-2026] MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search tools.
3 captures since 2026-05-23
setup.py
· python · 0 dependencies