[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.
Appears on
Quick read
Latest capture 2026-10-16 03:14
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
0 paths
Agent instructions and tool configuration found in this repository.
No config files detected.
8 observed captures since 2026-05-23. Observed captures are shown by default.
Stars from first capture +41
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Solve Visual Understanding with Reinforced VLMs
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
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
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)
