{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T21:38:39Z","timestamp":1789508319144,"version":"build-2803163510"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819540877","type":"print"},{"value":"9789819540884","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T00:00:00Z","timestamp":1762646400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-4088-4_35","type":"book-chapter","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T14:14:39Z","timestamp":1762611279000},"page":"507-520","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["M2RAG: A Multi-agent and\u00a0Multimodal Fusion Framework for\u00a0Retrieval-Augmented Document QA"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7021-639X","authenticated-orcid":false,"given":"Tongtong","family":"Duan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guotong","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhunchen","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,9]]},"reference":[{"key":"35_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"35_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"35_CR3","unstructured":"Bang, Y., et\u00a0al.: A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity. arXiv preprint arXiv:2302.04023 (2023)"},{"key":"35_CR4","unstructured":"Chan, C.M., et al.: Chateval: towards better LLM-based evaluators through multi-agent debate. arXiv preprint arXiv:2308.07201 (2023)"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Chen, W., Hu, H., Chen, X., Verga, P., Cohen, W.W.: Murag: multimodal retrieval-augmented generator for open question answering over images and text. arXiv preprint arXiv:2210.02928 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.375"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Cho, J., Mahata, D., Irsoy, O., He, Y., Bansal, M.: M3docrag: multi-modal retrieval is what you need for multi-page multi-document understanding. arXiv preprint arXiv:2411.04952 (2024)","DOI":"10.1109\/ICCVW69036.2025.00649"},{"key":"35_CR7","unstructured":"Deng, C., et\u00a0al.: Longdocurl: a comprehensive multimodal long document benchmark integrating understanding, reasoning, and locating. arXiv preprint arXiv:2412.18424 (2024)"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Ding, Y., Luo, S., Chung, H., Han, S.C.: VQA: a new dataset for real-world VQA on pdf documents. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 585\u2013601. Springer (2023)","DOI":"10.1007\/978-3-031-43427-3_35"},{"key":"35_CR9","unstructured":"Ghosh, S., et al.: VDGD: mitigating LVLM hallucinations in cognitive prompts by bridging the visual perception gap. arXiv e-prints pp. arXiv-2405 (2024)"},{"issue":"12","key":"35_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji, Z., et al.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 1\u201338 (2023)","journal-title":"ACM Comput. Surv."},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Kannan, S.S., Venkatesh, V.L., Min, B.C.: Smart-LLM: smart multi-agent robot task planning using large language models. In: 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 12140\u201312147. IEEE (2024)","DOI":"10.1109\/IROS58592.2024.10802322"},{"key":"35_CR12","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Li, B., Wang, Y., Gu, J., Chang, K.W., Peng, N.: Metal: a multi-agent framework for chart generation with test-time scaling. arXiv preprint arXiv:2502.17651 (2025)","DOI":"10.18653\/v1\/2025.acl-long.1452"},{"key":"35_CR14","unstructured":"Li, Y., et\u00a0al.: Benchmarking multimodal retrieval augmented generation with dynamic VQA dataset and self-adaptive planning agent. arXiv preprint arXiv:2411.02937 (2024)"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Ma, X., Zhuang, S., Koopman, B., Zuccon, G., Chen, W., Lin, J.: Visa: retrieval augmented generation with visual source attribution. arXiv preprint arXiv:2412.14457 (2024)","DOI":"10.18653\/v1\/2025.acl-long.1456"},{"key":"35_CR16","unstructured":"Ma, Y., et al.: Mmlongbench-doc: benchmarking long-context document understanding with visualizations. arXiv preprint arXiv:2407.01523 (2024)"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: Docvqa: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"35_CR18","doi-asserted-by":"publisher","first-page":"142642","DOI":"10.1109\/ACCESS.2020.3012542","volume":"8","author":"J Memon","year":"2020","unstructured":"Memon, J., Sami, M., Khan, R.A., Uddin, M.: Handwritten optical character recognition (OCR): a comprehensive systematic literature review (SLR). IEEE Access 8, 142642\u2013142668 (2020)","journal-title":"IEEE Access"},{"key":"35_CR19","unstructured":"Mialon, G., et\u00a0al.: Augmented language models: a survey. arXiv preprint arXiv:2302.07842 (2023)"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Mishra, A., Shekhar, S., Singh, A.K., Chakraborty, A.: OCR-VQA: visual question answering by reading text in images. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 947\u2013952. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"35_CR21","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Robertson, S.E., Walker, S., Jones, S., Hancock-Beaulieu, M.M., Gatford, M., et al.: Okapi at TREC-3. NIST Special Publication SP 109, 109 (1995)","DOI":"10.6028\/NIST.SP.500-225.city"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract OCR engine. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), vol.\u00a02, pp. 629\u2013633. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Suri, M., Mathur, P., Dernoncourt, F., Goswami, K., Rossi, R.A., Manocha, D.: Visdom: multi-document QA with visually rich elements using multimodal retrieval-augmented generation. arXiv preprint arXiv:2412.10704 (2024)","DOI":"10.18653\/v1\/2025.naacl-long.310"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Tanaka, R., Nishida, K., Nishida, K., Hasegawa, T., Saito, I., Saito, K.: Slidevqa: a dataset for document visual question answering on multiple images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 13636\u201313645 (2023)","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"35_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109834","volume":"144","author":"R Tito","year":"2023","unstructured":"Tito, R., Karatzas, D., Valveny, E.: Hierarchical multimodal transformers for multipage docvqa. Pattern Recogn. 144, 109834 (2023)","journal-title":"Pattern Recogn."},{"key":"35_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Vidorag: visual document retrieval-augmented generation via dynamic iterative reasoning agents. arXiv preprint arXiv:2502.18017 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.464"},{"key":"35_CR28","unstructured":"Xu, Z., et al.: Activerag: autonomously knowledge assimilation and accommodation through retrieval-augmented agents. arXiv preprint arXiv:2402.13547 (2024)"},{"key":"35_CR29","unstructured":"Yu, S., et\u00a0al.: Visrag: vision-based retrieval-augmented generation on multi-modality documents. arXiv preprint arXiv:2410.10594 (2024)"},{"key":"35_CR30","doi-asserted-by":"crossref","unstructured":"Zou, A., et al.: Docbench: a benchmark for evaluating LLM-based document reading systems. arXiv preprint arXiv:2407.10701 (2024)","DOI":"10.18653\/v1\/2025.knowledgenlp-1.29"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4088-4_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:06:48Z","timestamp":1781568408000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4088-4_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,9]]},"ISBN":["9789819540877","9789819540884"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4088-4_35","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,9]]},"assertion":[{"value":"9 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}