論文 深掘り Hugging Face 発表: 2026-05-26 HF ↑63

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

著者: Minki Kang, Shizhe Diao, Ryo Hachiuma, Sung Ju Hwang, Pavlo Molchanov ほか2名

要約

Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning alone often cannot resolve. Agentic reasoning therefore interleaves two behaviors with a structural asymmetry: thinking (the self-contained default)…

#agent#multimodal#rl#benchmark

同じカテゴリの記事