{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:02:46Z","timestamp":1789376566482,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372345","type":"print"},{"value":"9783032372352","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-37235-2_8","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:06:47Z","timestamp":1789373207000},"page":"127-143","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ProMSA: Progressive Multimodal Search Agents for\u00a0Knowledge-Based Visual Question Answering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2318-5665","authenticated-orcid":false,"given":"ZhengXian","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0110-3963","authenticated-orcid":false,"given":"Hangrui","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2925-3995","authenticated-orcid":false,"given":"Kai","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuohong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunyao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanrui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zirui","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoqian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"8_CR1","unstructured":"Achiam, J., et al.: GPT-4 Technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"8_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL Technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"8_CR3","unstructured":"Bai, S., et al.: Qwen2.5-VL Technical report (2025). https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Caffagni, D., et al.: Wiki-llava: hierarchical retrieval-augmented generation for multimodal llms. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1818\u20131826 (2024)","DOI":"10.1109\/CVPRW63382.2024.00188"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., Liu, Z.: M3-embedding: multilinguality, multi-functionality, multi-granularity text embeddings through selfknowledge distillation. In: Findings of the association for computational linguistics: ACL 2024, pp. 2318\u20132335 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Compcap: improving multimodal large language models with composite captions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23582\u201323592 (2025)","DOI":"10.1109\/ICCV51701.2025.02189"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Can pre-trained vision and language models answer visual information-seeking questions? In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 14948\u201314968 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"8_CR8","unstructured":"Chng, Y.X., et al.: Sensenova-mars: empowering multimodal agentic reasoning and search via reinforcement learning. arXiv preprint arXiv:2512.24330 (2025)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Cocchi, F., Moratelli, N., Cornia, M., Baraldi, L., Cucchiara, R.: Augmenting multimodal LLMs with self-reflective tokens for knowledge-based visual question answering. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 9199\u20139209 (2025)","DOI":"10.1109\/CVPR52734.2025.00859"},{"key":"8_CR10","unstructured":"Compagnoni, A., et al.: Reag: reasoning-augmented generation for knowledge based visual question answering. arXiv preprint arXiv:2511.22715 (2025)"},{"key":"8_CR11","unstructured":"Hong, J., Zhao, C., Zhu, C., Lu, W., Xu, G., Yu, X.: Deepeyesv2: toward agentic multimodal model. arXiv preprint arXiv:2511.05271 (2025)"},{"key":"8_CR12","unstructured":"Hong, Y., et al.: Cc-vqa: conflict-and correlation-aware method for mitigating knowledge conflict in knowledge-based visual question answering. arXiv preprint arXiv:2602.23952 (2026)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Hong, Y., et al.: Knowledge-based visual question answer with multimodal processing, retrieval and filtering. arXiv preprint arXiv:2510.14605 (2025)","DOI":"10.52202\/085713-3980"},{"key":"8_CR14","unstructured":"Jin, B., et al.: Search-r1: training LLMs to reason and leverage search engines with reinforcement learning. arXiv preprint arXiv:2503.09516 (2025)"},{"key":"8_CR15","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Search-o1: agentic search-enhanced large reasoning models. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 5420\u20135438 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.276"},{"key":"8_CR17","unstructured":"Ling, Z., et al.: Mmkbrag: a multi-modal knowledge-based retrieval-augmented generation framework. arXiv preprint arXiv:2504.10074 (2025)"},{"key":"8_CR18","unstructured":"Mao, X., et al.: Mas-vqa: a mask-and-select framework for knowledge-based visual question answering. arXiv preprint arXiv:2602.15915 (2026)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Ok-vqa: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3195\u20133204 (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Mensink, T., et al.: Encyclopedic VQA: visual questions about detailed properties of fine-grained categories. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3113\u20133124 (2023)","DOI":"10.1109\/ICCV51070.2023.00289"},{"key":"8_CR21","unstructured":"Shao, Z., et\u00a0al.: Deepseekmath: pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"8_CR22","unstructured":"Sheng, G., et al.: Hybridflow: a flexible and efficient RLHF framework. arXiv preprint arXiv: 2409.19256 (2024)"},{"key":"8_CR23","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: Eva-clip: improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Wang, P., Li, Z.Z., Yin, F., Ran, D., Liu, C.L.: Mv-math: evaluating multimodal math reasoning in multi-visual contexts. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 19541\u201319551 (2025)","DOI":"10.1109\/CVPR52734.2025.01820"},{"key":"8_CR25","unstructured":"Wang, Z., et al.: Escapecraft: a 3D room escape environment for benchmarking complex multimodal reasoning ability. arXiv preprint arXiv:2503.10042 (2025)"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Mmsearch-r1: incentivizing LLMs to search. arXiv preprint arXiv:2506.20670 (2025)","DOI":"10.18653\/v1\/2026.acl-long.114"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Yan, Y., Xie, W.: Echosight: advancing visual-language models with wiki knowledge. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 1538\u20131551 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.83"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Yang, W., Fu, J., Wang, R., Wang, J., Song, L., Bian, J.: Omgm: orchestrate multiple granularities and modalities for efficient multimodal retrieval. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 24545\u201324563 (2025)","DOI":"10.18653\/v1\/2025.acl-long.1198"},{"key":"8_CR29","unstructured":"Ye, K., et al.: Real: resolving knowledge conflicts in knowledge-intensive visual question answering via reasoning-pivot alignment. arXiv preprint arXiv:2602.14065 (2026)"},{"key":"8_CR30","unstructured":"Ye, W., et al.: Qkvqa: question-focused filtering for knowledge-based VQA (2026). https:\/\/arxiv.org\/abs\/2601.13856"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Yin, S., et al.: A survey on multimodal large language models. National Sci. Rev. 11(12), nwae403 (2024)","DOI":"10.1093\/nsr\/nwae403"},{"key":"8_CR32","unstructured":"Zheng, C., et\u00a0al.: Group sequence policy optimization. arXiv preprint arXiv:2507.18071 (2025)"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: Llamafactory: unified efficient fine-tuning of 100+ language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). Association for Computational Linguistics, Bangkok, Thailand (2024). http:\/\/arxiv.org\/abs\/2403.13372","DOI":"10.18653\/v1\/2024.acl-demos.38"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37235-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:07:06Z","timestamp":1789373226000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37235-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372345","9783032372352"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37235-2_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"15 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}