Data incompleteness severely impedes the reliability of multimodal systems. Existing reconstruction methods face distinct bottlenecks: conventional parametric/generative models are prone to hallucinations due to over-reliance on internal memory, while retrieval-augmented frameworks struggle with retrieval rigidity. Critically, these end-to-end architectures are fundamentally constrained by Semantic-Detail Entanglement -- a structural conflict between logical reasoning and signal synthesis that compromises fidelity. In this paper, we present \textbf{\underline{O}}mni-\textbf{\underline{M}}odality \textbf{\underline{G}}eneration Agent (\textbf{OMG-Agent}), a novel framework that shifts the paradigm from static mapping to a dynamic coarse-to-fine Agentic Workflow. By mimicking a \textit{deliberate-then-act} cognitive process, OMG-Agent explicitly decouples the task into three synergistic stages: (1) an MLLM-driven Semantic Planner that resolves input ambiguity via Progressive Contextual Reasoning, creating a deterministic structured semantic plan; (2) a non-parametric Evidence Retriever that grounds abstract semantics in external knowledge; and (3) a Retrieval-Injected Executor that utilizes retrieved evidence as flexible feature prompts to overcome rigidity and synthesize high-fidelity details. Extensive experiments on multiple benchmarks demonstrate that OMG-Agent consistently surpasses state-of-the-art methods, maintaining robustness under extreme missingness, e.g., a 2.6-point gain on CMU-MOSI at 70\% missing rates.
@article{arxiv.2602.04144,
title = {OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows},
author = {Ruiting Dai and Zheyu Wang and Haoyu Yang and Yihan Liu and Chengzhi Wang and Zekun Zhang and Zishan Huang and Jiaman Cen and Lisi Mo},
journal= {arXiv preprint arXiv:2602.04144},
year = {2026}
}