InternLM

InternLM/ARM-Thinker

[CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"

2 good first / help-wanted issues · Python · last activity Jun 30, 2026

agentic-rl llm reward-modeling think-with-image vision-language-model vlm
2 Open Issues Need Help Last updated: Jun 30, 2026

Open Issues Need Help

View All on GitHub
documentation enhancement good first issue help wanted
InternLM/ARM-Thinker
193

[CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"

Python
#agentic-rl#llm#reward-modeling#think-with-image#vision-language-model#vlm
documentation good first issue
InternLM/ARM-Thinker
193

[CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"

Python
#agentic-rl#llm#reward-modeling#think-with-image#vision-language-model#vlm