Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions

ArXi:2604.15917v1 Announce Type: new Instruction guided image editing has advanced substantially with recent generative models, yet it still fails to produce reliable results across many seemingly simple cases. We observe that a large portion of these failures stem not from insufficient model capacity, but from poorly formulated editing tasks, such as those involving small targets, implicit spatial relations, or under-specified instructions.