The authors withdraw this preprint because substantial changes to the core methodology and scope of the research mean that the original manuscript no longer accurately represents the work we intend to present. These changes go beyond a conventional revision, and we do not consider a replacement version appropriate
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.
Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
Beijing Institute of Technology(北京理工大学);State Key Laboratory of General Artificial Intelligence, BIGAI(通用人工智能国家重点实验室,BIGAI);DataCanvas;Beijing University of Posts and Telecommunications(北京邮电大学);Shenzhen MSU-BIT University(深圳MSU-BIT大学)
CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
Microsoft Research Asia(微软亚洲研究院);Department of Biomedical Engineering, Yale University(耶鲁大学生物医学工程系);Department of Radiology & Biomedical Imaging, Yale University(耶鲁大学放射学与生物医学成像系)
TheoremForge: Scaling up Formal Data Synthesis with Low-Budget Agentic Workflow
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学全球化人工智能学院);Beijing Key Laboratory of Research on Large Models(北京大模型研究关键实验室);Engineering Research Center of Next-Generation Intelligent Search(下一代智能搜索与推荐工程研究中心)
AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models
Institute of Artificial Intelligence, Beihang University(北京航空航天大学人工智能研究院);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);University of Science and Technology Beijing(北京科技大学)
JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG
Renmin University of China(中国人民大学);Xiaohongshu Inc.(小红书公司);Institute of Automation,Chinese Academy of Sciences(中国科学院自动化研究所);Shanghai AI Laboratory(上海人工智能实验室)
Lightweight Quantum Agent for Edge Systems: Joint PQC and NOMA Resource Allocation
School of Computer, Electronics and Information, Guangxi University(广西大学计算机电子与信息学院);Guangxi Key Laboratory of Multimedia Communications and Network Technology(广西多媒体通信与网络技术重点实验室);School of Computer Science and Engineering, Central South University(中南大学计算机科学与工程学院);College of Cyber Security, Jinan University(暨南大学网络安全学院);School of Computer Science and Engineering, South China University of Technology(华南理工大学计算机科学与工程学院);Pazhou Laboratory(琶洲实验室);Faculty of Computers and Artificial Intelligence, Hurghada University(Hurghada大学计算机与人工智能学院);Department of Information Systems, University of Maryland, Baltimore County (UMBC)(美国马里兰大学巴尔的摩县分校信息系统系)