{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:55:02Z","timestamp":1776444902040,"version":"3.51.2"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323162","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["MMM-RAG: A Multi-Agent Multi-Feature Method for Multimodal Retrieval-Augmented Generation"],"prefix":"10.1109","author":[{"given":"Tianyou","family":"Chang","sequence":"first","affiliation":[{"name":"Shanghai Spacelight Precision Machinery Institute,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yupeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00847"},{"key":"ref3","first-page":"9459","article-title":"Retrievalaugmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref4","article-title":"Retrieval-augmented generation for large language models: A survey","volume":"2","author":"Gao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"Vdocrag: Retrieval-augmented generation over visually-rich documents","volume-title":"arXiv preprint arXiv","author":"Yang","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/AIxSET62544.2024.00030"},{"key":"ref7","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref8","first-page":"19730","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref9","article-title":"Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","article-title":"Qwen3 embedding: Advancing text embedding and reranking through foundation models","author":"Zhang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref11","volume-title":"LlamaIndex","author":"Liu","year":"2022"},{"key":"ref12","article-title":"Qwen2 technical report","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref14","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v12i1.14983"},{"key":"ref16","article-title":"Qwen3 technical report","author":"Yang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"ref18","article-title":"Visrag: Vision-based retrieval-augmented generation on multi-modality documents","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"A comprehensive survey of retrieval-augmented generation (rag): Evolution, current landscape and future directions","author":"Gupta","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","article-title":"Agentic retrievalaugmented generation: A survey on agentic rag","author":"Singh","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Longrag: Enhancing retrieval-augmented generation with long-context 11 ms","author":"Jiang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.495"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323162.pdf?arnumber=11323162","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:09:45Z","timestamp":1768460985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323162\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323162","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}