AI RESEARCH
IMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection
arXiv CS.AI
•
ArXi:2603.29602v1 Announce Type: cross Existing multi-turn image editing paradigms are often confined to isolated single-step execution. Due to a lack of context-awareness and closed-loop feedback mechanisms, they are prone to error accumulation and semantic drift during multi-turn interactions, ultimately resulting in severe structural distortion of the generated images.