2h agoAXPO Method Improves Multimodal Agent Reasoning in Vision-Language Models——0——Original postOPAK#28AK|@_AKHALIQAgent Explorative Policy Optimization for Multimodal Agentic Reasoning8:29 AM · May 28, 2026 View on XREPLYAK#28AK|@_AKHALIQpaper: https://huggingface.co/papers/2605.28774AKAK@_akhaliqAgent Explorative Policy Optimization for Multimodal Agentic Reasoning3:29 PM · May 28, 2026 · 3.6K Views3:29 PM · May 28, 2026 · 2.9K Views
REPLYAK#28AK|@_AKHALIQpaper: https://huggingface.co/papers/2605.28774AKAK@_akhaliqAgent Explorative Policy Optimization for Multimodal Agentic Reasoning3:29 PM · May 28, 2026 · 3.6K Views3:29 PM · May 28, 2026 · 2.9K Views
AKAK@_akhaliq