AI RESEARCH
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
arXiv CS.CL
•
ArXi:2605.28774v1 Announce Type: new 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) and tool use (a high-variance auxiliary acting). We refer to this asymmetry as the Thinking-Acting Gap. Under standard RL recipes like GRPO, the gap manifests as two diagnostic symptoms during.