2026-10-11T08:31:09Z https://www.scidb.cn/oai

10.57760/sciencedb.011db 2026-09-03T11:12:18Z

2026-09-03 Code and Experimental Data for Interleaved Text-Image Generation Based on Multi-Agent Debate doi:10.57760/sciencedb.011db en This dataset is the related scientific research data of the paper "Method for Generating Image Text Interweaving Based on Multi Agent Debate". It mainly includes the implementation code of the multi-agent debate image text interweaving generation method proposed in the paper, the text inference agent, the visual perception agent, and the global arbitration agent modules, the multi round debate and conflict resolution module, the prompt word template, the data processing and evaluation script, as well as the relevant output files and configuration instructions for reproducing experimental results. The paper experiment is based on MRAMG Bench, and the original MRAMG Bench data is not duplicated in this dataset. Users need to obtain it separately according to the requirements of the original dataset publisher.  Multimodal Retrieval-Augmented Generation (Multimodal RAG / MM-RAG); Interleaved Image-Text Generation; Multi-Agent Debate; Multimodal Large Language Model (MLLM)​ 或 Large Multimodal Model (LMM) 马杰 Zhang Hanchi Qu Ning Xue Haoquan Wang Xinping Liu Jun PUBLIC https://api.github.com/licenses/apache-2.0 dataset Science Data Bank