RUCAIBox/R1-Searcher
R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Learn to resolve ambiguity for Question Answering through RL
R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
Simple RL training for reasoning
No description.
[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.
2 captures since 2026-05-23