Alibaba-NLP/ZeroSearch
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
No description.
A High-Efficiency System of Large Language Model Based Search Agents
[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.
[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)
2 captures since 2026-05-23