AI RESEARCH
What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation
arXiv CS.CV
•
ArXi:2602.11499v2 Announce Type: replace Multimodal Large Language Models have shown promising capabilities in bridging visual and textual reasoning, yet their reasoning capabilities in Open-Vocabulary Human-Object Interaction (OV-HOI) are limited by cross-modal hallucinations and limited viewpoints of images. To address this, we propose ImagineAgent, an agentic framework that integrates cognitive mapping, tool-augmented reinforcement learning (RL), and generative world modeling for robust OV-HOI understanding.