{"ID":5551671,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T13:20:54.626185648Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00920","arxiv_id":"2607.00920","title":"GMO-E$^2$DIT: Grounded Multi-Operation Editing for E-Commerce Images","abstract":"Real-world e-commerce image editing often requires multiple, localized, and auditable operations rather than global restyling. This compositional nature poses a dual challenge: models must precisely apply all requested edits to the correct regions while preserving unmodified content, even under ambiguous instructions. Existing one-shot editors conflate intent resolution, spatial grounding, and synthesis into a single step, frequently resulting in partial execution failures, which is unacceptable for commercial scenarios. To address this, we introduce GMO-E$^2$DIT, an agentic editing framework that couples a Vision-Language Model (VLM) with a mask-conditioned image editor to tackle structured multi-turn task completion. Given an underspecified instruction, the VLM agent constructs a region-grounded edit agenda, effectively decoupling cognitive reasoning from generative rendering. The framework then executes sub-programs via operation-aware masks and references, utilizing a reflection-driven loop to inspect intermediate results and determine the subsequent state. This iterative mechanism reliably preserves safe partial progress, retries unfinished operations, and recovers from errors. Furthermore, we develop a unified data pipeline providing aligned supervision for planning, execution, and reflection, alongside EComEditBench, a comprehensive benchmark for instruction-driven evaluation. Extensive experiments demonstrate that GMO-E$^2$DIT achieves competitive performance compared to strong closed-source models, yielding superior instruction accuracy and edit fidelity over existing baselines.","short_abstract":"Real-world e-commerce image editing often requires multiple, localized, and auditable operations rather than global restyling. This compositional nature poses a dual challenge: models must precisely apply all requested edits to the correct regions while preserving unmodified content, even under ambiguous instructions....","url_abs":"https://arxiv.org/abs/2607.00920","url_pdf":"https://arxiv.org/pdf/2607.00920v1","authors":"[\"Zipeng Guo\",\"Xiaoan Liu\",\"Lichen Ma\",\"Cheng Wang\",\"Yu He\",\"Xiaolong Fu\",\"Jingling Fu\",\"Xinyuan Shan\",\"Shaojie Guo\",\"Luohang Liu\",\"Junshi Huang\",\"Yan Li\"]","published":"2026-07-01T13:23:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}