ARM-Thinker: Agentic multimodal reward model that calls tools for verifiable judgments
Original title🔥Introducing ARM-Thinker, the first Agentic multimodal Reward Model that autonomously invokes external tools to ground judgments in veri...
AISummary
Intern Large Models introduced ARM-Thinker, an agentic multimodal reward model that autonomously invokes image crop and zoom-in, document retrieval, and instruction-following validators to ground its judgments in evidence.
Source: Intern Large Models · x.comPublished · added here