{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T09:13:49Z","timestamp":1789118029251,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":87,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371669","type":"print"},{"value":"9783032371676","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\/978-3-032-37167-6_32","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T08:49:27Z","timestamp":1789116567000},"page":"554-577","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MG$$^2$$-RAG: Multi-granularity Graph for\u00a0Multimodal Retrieval-Augmented Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7912-0987","authenticated-orcid":false,"given":"Sijun","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1120-4685","authenticated-orcid":false,"given":"Qiang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3700-6759","authenticated-orcid":false,"given":"Xiaoxing","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2316-5478","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Alam, F., Ofli, F., Imran, M.: CrisisMMD: multimodal Twitter datasets from natural disasters. In: Proceedings of the International AAAI Conference on Web and Social Media (AAAI), vol.\u00a012 (2018). https:\/\/ojs.aaai.org\/index.php\/ICWSM\/article\/view\/14983","DOI":"10.1609\/icwsm.v12i1.14983"},{"key":"32_CR2","unstructured":"Asai, A., Wu, Z., Wang, Y., Sil, A., Hajishirzi, H.: Self-RAG: learning to retrieve, generate, and critique through self-reflection. In: The Twelfth International Conference on Learning Representations (ICLR), vol.\u00a02024, pp. 9112\u20139141 (2024). https:\/\/openreview.net\/forum?id=hSyW5go0v8"},{"key":"32_CR3","unstructured":"Bai, S., Cet al.: Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025). https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Bulian, J., Buck, C., Gajewski, W., B\u00f6rschinger, B., Schuster, T.: Tomayto, Tomahto. Beyond token-level answer equivalence for question answering evaluation. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 291\u2013305 (2022). https:\/\/aclanthology.org\/2022.emnlp-main.20\/","DOI":"10.18653\/v1\/2022.emnlp-main.20"},{"key":"32_CR5","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 (CVPR), pp. 1818\u20131826 (2024). https:\/\/openaccess.thecvf.com\/content\/CVPR2024W\/MMFM\/html\/Caffagni_Wiki-LLaVA_Hierarchical_Retrieval-Augmented_Generation_for_Multimodal_LLMs_CVPRW_2024_paper.html","DOI":"10.1109\/CVPRW63382.2024.00188"},{"key":"32_CR6","unstructured":"Carion, N., et al.: SAM 3: Segment Anything with Concepts. arXiv preprint arXiv:2511.16719 (2025). https:\/\/arxiv.org\/abs\/2511.16719"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Chen, D., Fisch, A., Weston, J., Bordes, A.: Reading Wikipedia to answer open-domain questions. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 1870\u20131879 (2017). https:\/\/aclanthology.org\/P17-1171\/","DOI":"10.18653\/v1\/P17-1171"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L., Tong, P., Jin, Z., Sun, Y., Ye, J., Xiong, H.: Plan-on-graph: self-correcting adaptive planning of large language model on knowledge graphs. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), vol.\u00a037, pp. 37665\u201337691 (2024). https:\/\/openreview.net\/forum?id=CwCUEr6wO5","DOI":"10.52202\/079017-1189"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Chen, W., Hu, H., Chen, X., Verga, P., Cohen, W.: MuRAG: multimodal retrieval-augmented generator for open question answering over images and text. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 5558\u20135570 (2022). https:\/\/aclanthology.org\/2022.emnlp-main.375\/","DOI":"10.18653\/v1\/2022.emnlp-main.375"},{"key":"32_CR10","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 (EMNLP), pp. 14948\u201314968 (2023). https:\/\/aclanthology.org\/2023.emnlp-main.925\/","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, Q., et al.: Unified active retrieval for retrieval augmented generation. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 17153\u201317166 (2024). https:\/\/aclanthology.org\/2024.findings-emnlp.999\/","DOI":"10.18653\/v1\/2024.findings-emnlp.999"},{"key":"32_CR12","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 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9199\u20139209 (2025). https:\/\/openaccess.thecvf.com\/content\/CVPR2025\/html\/Cocchi_Augmenting_Multimodal_LLMs_with_Self-Reflective_Tokens_for_Knowledge-based_Visual_Question_CVPR_2025_paper.html","DOI":"10.1109\/CVPR52734.2025.00859"},{"key":"32_CR13","unstructured":"Compagnoni, A., et al.: ReAG: Reasoning-augmented generation for knowledge-based visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11901\u201311911 (2026). https:\/\/openaccess.thecvf.com\/content\/CVPR2026\/html\/Compagnoni_ReAG_Reasoning-Augmented_Generation_for_Knowledge-based_Visual_Question_Answering_CVPR_2026_paper.html"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Dai, W., et al.: InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. In: Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS), vol.\u00a036, pp. 49250\u201349267 (2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/hash\/9a6a435e75419a836fe47ab6793623e6-Abstract-Conference.html","DOI":"10.52202\/075280-2142"},{"key":"32_CR15","unstructured":"Dong, J., et al.: Youtu-GraphRAG: vertically unified agents for graph retrieval-augmented complex reasoning. In: The Fourteenth International Conference on Learning Representations (ICLR) (2026). https:\/\/openreview.net\/forum?id=yCtgZ2G39E"},{"key":"32_CR16","unstructured":"Edge, D., et al.: From Local to Global: A Graph RAG Approach to Query-Focused Summarization. arXiv preprint arXiv:2404.16130 (2024). https:\/\/arxiv.org\/abs\/2404.16130"},{"key":"32_CR17","unstructured":"Edge, D., Trinh, H., Larson, J.: LazyGraphRAG: Setting a New Standard for Quality and Cost (2024). https:\/\/www.microsoft.com\/en-us\/research\/blog\/lazygraphrag-setting-a-new-standard-for-quality-and-cost\/"},{"key":"32_CR18","unstructured":"Faysse, M., et al.: ColPali: efficient document retrieval with vision language models. In: The Thirteenth International Conference on Learning Representations (ICLR), vol.\u00a02025, pp. 61424\u201361449 (2025). https:\/\/openreview.net\/forum?id=ogjBpZ8uSi"},{"key":"32_CR19","unstructured":"Gao, J., et al.: SmartRAG: jointly learn RAG-related tasks from the environment feedback. In: The Thirteenth International Conference on Learning Representations (ICLR), vol.\u00a02025, pp. 53117\u201353140 (2025). https:\/\/openreview.net\/forum?id=OCd3cffulp"},{"key":"32_CR20","unstructured":"Google DeepMind Team: Gemini 3.1 Pro: Best for Complex Tasks and Bringing Creative Concepts to Life (2026). https:\/\/deepmind.google\/models\/gemini\/pro\/"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the v in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6904\u20136913 (2017). https:\/\/openaccess.thecvf.com\/content_cvpr_2017\/html\/Goyal_Making_the_v_CVPR_2017_paper.html","DOI":"10.1109\/CVPR.2017.670"},{"key":"32_CR22","unstructured":"Guan, X., et al.: DeepRAG: thinking to retrieval step by step for large language models. In: The 14th International Conference on Learning Representations (ICLR) (2026). https:\/\/openreview.net\/pdf?id=VI2YaggHIF"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Guo, Z., Xia, L., Yu, Y., Ao, T., Huang, C.: LightRAG: simple and fast retrieval-augmented generation. In: Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 10746\u201310761 (2025). https:\/\/aclanthology.org\/2025.findings-emnlp.568\/","DOI":"10.18653\/v1\/2025.findings-emnlp.568"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Guti\u00e9rrez, B.J., Shu, Y., Gu, Y., Yasunaga, M., Su, Y.: HippoRAG: neurobiologically inspired long-term memory for large language models. In: Proceedings of the 38th International Conference on Neural Information Processing Systems (NeurIPS), vol.\u00a037, pp. 59532\u201359569 (2024). https:\/\/openreview.net\/forum?id=hkujvAPVsg.","DOI":"10.52202\/079017-1902"},{"key":"32_CR25","unstructured":"Guti\u00e9rrez, B.J., Shu, Y., Qi, W., Zhou, S., Su, Y.: From RAG to Memory: Non-Parametric Continual Learning for Large Language Models. In: International Conference on Machine Learning (ICML), pp. 21497\u201321515 (2025). https:\/\/openreview.net\/forum?id=LWH8yn4HS2"},{"key":"32_CR26","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.: Retrieval augmented language model pre-training. In: Proceedings of the 37th International Conference on Machine Learning (ICML), pp. 3929\u20133938 (2020). https:\/\/proceedings.mlr.press\/v119\/guu20a.html"},{"key":"32_CR27","unstructured":"Hao, J., Liu, H., Xiao, X., Huang, Q., Yu, J.: Uni-X: mitigating modality conflict with a two-end-separated architecture for unified multimodal models. In: The Fourteenth International Conference on Learning Representations (ICLR) (2026). https:\/\/openreview.net\/forum?id=IJLIYpCkwz"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Haveliwala, T.H.: Topic-sensitive pagerank. In: Proceedings of the 11th international conference on World Wide Web (WWW), pp. 517\u2013526 (2002). https:\/\/dl.acm.org\/doi\/abs\/10.1145\/511446.511513","DOI":"10.1145\/511446.511513"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"He, X., et al.: G-Retriever: retrieval-augmented generation for textual graph understanding and question answering. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), vol.\u00a037, pp. 132876\u2013132907 (2024). https:\/\/openreview.net\/forum?id=MPJ3oXtTZl","DOI":"10.52202\/079017-4224"},{"key":"32_CR30","unstructured":"Honnibal, M., Montani, I., Van\u00a0Landeghem, S., Boyd, A.: spaCy: Industrial-Strength Natural Language Processing in Python (2020). https:\/\/spacy.io\/"},{"key":"32_CR31","unstructured":"Hsu, S., Khattab, O., Finn, C., Sharma, A.: Grounding by trying: LLMs with reinforcement learning-enhanced retrieval. In: The Thirteenth International Conference on Learning Representations (ICLR), vol.\u00a02025, pp. 26136\u201326152 (2025). https:\/\/openreview.net\/forum?id=BPAZ6yW3K7"},{"key":"32_CR32","unstructured":"Hu, C.W., et al.: mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation. arXiv preprint arXiv:2505.24073 (2025). https:\/\/arxiv.org\/abs\/2505.24073"},{"key":"32_CR33","doi-asserted-by":"crossref","unstructured":"Hu, Z., et al.: REVEAL: Retrieval-augmented visual-language pre-training with multi-source multimodal knowledge memory. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23369\u201323379 (2023). https:\/\/openaccess.thecvf.com\/content\/CVPR2023\/html\/Hu_REVEAL_Retrieval-Augmented_Visual-Language_Pre-Training_With_Multi-Source_Multimodal_Knowledge_Memory_CVPR_2023_paper.html","DOI":"10.1109\/CVPR52729.2023.02238"},{"key":"32_CR34","doi-asserted-by":"crossref","unstructured":"Huang, L., et al.: A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions. ACM Trans. Inf. Syst. (TOIS) 43(2), 1\u201355 (2025). https:\/\/dl.acm.org\/doi\/full\/10.1145\/3703155","DOI":"10.1145\/3703155"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zhang, S., Xiao, X.: KET-RAG: a cost-efficient multi-granular indexing framework for graph-RAG. In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 1003\u20131012 (2025). https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3711896.3737012","DOI":"10.1145\/3711896.3737012"},{"key":"32_CR36","doi-asserted-by":"crossref","unstructured":"Jin, B., et al.: Graph chain-of-thought: augmenting large language models by reasoning on graphs. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 163\u2013184 (2024). https:\/\/aclanthology.org\/2024.findings-acl.11\/","DOI":"10.18653\/v1\/2024.findings-acl.11"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Krishna, R., et al.: Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision (IJCV) 123(1), 32\u201373 (2017). https:\/\/link.springer.com\/article\/10.1007\/S11263-016-0981-7","DOI":"10.1007\/s11263-016-0981-7"},{"key":"32_CR38","unstructured":"Lazaridou, A., Gribovskaya, E., Stokowiec, W., Grigorev, N.: Internet-augmented language models through few-shot prompting for open-domain question answering. arXiv preprint arXiv:2203.05115 (2022). https:\/\/arxiv.org\/abs\/2203.05115"},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Lee, J., Wang, Y., Li, J., Zhang, M.: Multimodal reasoning with multimodal knowledge graph. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 10767\u201310782 (2024). https:\/\/aclanthology.org\/2024.acl-long.579\/","DOI":"10.18653\/v1\/2024.acl-long.579"},{"key":"32_CR40","doi-asserted-by":"crossref","unstructured":"Lee, K., Chang, M.W., Toutanova, K.: Latent retrieval for weakly supervised open domain question answering. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 6086\u20136096 (2019). https:\/\/aclanthology.org\/P19-1612\/","DOI":"10.18653\/v1\/P19-1612"},{"key":"32_CR41","doi-asserted-by":"crossref","unstructured":"Lee, M., An, S., Kim, M.S.: PlanRAG: a plan-then-retrieval augmented generation for generative large language models as decision makers. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), pp. 6537\u20136555 (2024). https:\/\/aclanthology.org\/2024.naacl-long.364\/","DOI":"10.18653\/v1\/2024.naacl-long.364"},{"key":"32_CR42","unstructured":"Lee, Z., et al.: ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation. arXiv preprint arXiv:2503.21729 (2025). https:\/\/arxiv.org\/abs\/2503.21729"},{"key":"32_CR43","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS), pp. 9459\u20139474 (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/6b493230205f780e1bc26945df7481e5-Abstract.html"},{"key":"32_CR44","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: Proceedings of the 40th International Conference on Machine Learning (ICML), pp. 19730\u201319742 (2023). https:\/\/proceedings.mlr.press\/v202\/li23q"},{"key":"32_CR45","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Proceedings of the 39th International Conference on Machine Learning (ICML), pp. 12888\u201312900 (2022). https:\/\/proceedings.mlr.press\/v162\/li22n.html"},{"key":"32_CR46","unstructured":"Li, M., Miao, S., Li, P.: Simple is effective: the roles of graphs and large language models in knowledge-graph-based retrieval-augmented generation. In: International Conference on Learning Representations (ICLR), vol.\u00a02025, pp. 6061\u20136089 (2025). https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2025\/file\/11e1900e680f5fe1893a8e27362dbe2c-Paper-Conference.pdf"},{"key":"32_CR47","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 (EMNLP), pp. 5420\u20135438 (2025). https:\/\/aclanthology.org\/2025.emnlp-main.276\/","DOI":"10.18653\/v1\/2025.emnlp-main.276"},{"key":"32_CR48","doi-asserted-by":"crossref","unstructured":"Lim, Q.Z., Lee, C.P., Lim, K.M., Samingan, A.K.: UniRaG: unification, retrieval, and generation for multimodal question answering with pre-trained language models. IEEE Access 12, 71505\u201371519 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3403101","DOI":"10.1109\/ACCESS.2024.3403101"},{"key":"32_CR49","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26296\u201326306 (2024). https:\/\/openaccess.thecvf.com\/content\/CVPR2024\/html\/Liu_Improved_Baselines_with_Visual_Instruction_Tuning_CVPR_2024_paper.html","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"32_CR50","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS), vol.\u00a036, pp. 34892\u201334916 (2023). https:\/\/openreview.net\/forum?id=w0H2xGHlkw","DOI":"10.52202\/075280-1516"},{"key":"32_CR51","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Aligning vision to language: annotation-free multimodal knowledge graph construction for enhanced LLMs reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 981\u2013992 (2025). https:\/\/openaccess.thecvf.com\/content\/ICCV2025\/html\/Liu_Aligning_Vision_to_Language_Annotation-Free_Multimodal_Knowledge_Graph_Construction_for_ICCV_2025_paper","DOI":"10.1109\/ICCV51701.2025.00099"},{"key":"32_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-030-21348-0_30","volume-title":"The Semantic Web","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Li, H., Garcia-Duran, A., Niepert, M., Onoro-Rubio, D., Rosenblum, D.S.: MMKG: Multi-modal Knowledge Graphs. In: Hitzler, P., Fern\u00e1ndez, M., Janowicz, K., Zaveri, A., Gray, A.J.G., Lopez, V., Haller, A., Hammar, K. (eds.) ESWC 2019. LNCS, vol. 11503, pp. 459\u2013474. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-21348-0_30"},{"key":"32_CR53","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: Proceedings of the 36th International Conference on Neural Information Processing Systems (NeurIPS), vol.\u00a035, pp. 2507\u20132521 (2022). https:\/\/openreview.net\/forum?id=HjwK-Tc_Bc","DOI":"10.52202\/068431-0182"},{"key":"32_CR54","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Chameleon: plug-and-play compositional reasoning with large language models. In: Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS), vol.\u00a036, pp. 43447\u201343478 (2023). https:\/\/openreview.net\/forum?id=HtqnVSCj3q","DOI":"10.52202\/075280-1882"},{"key":"32_CR55","unstructured":"Luo, L., Li, Y.F., Haffari, G., Pan, S.: Reasoning on graphs: faithful and interpretable large language model reasoning. In: The Twelfth International Conference on Learning Representations (ICLR), vol.\u00a02024, pp. 14400\u201314423 (2024). https:\/\/openreview.net\/forum?id=ZGNWW7xZ6Q"},{"key":"32_CR56","doi-asserted-by":"crossref","unstructured":"Luo, L., Zhao, Z., Haffari, G., Phung, D., Gong, C., Pan, S.: GFM-RAG: graph foundation model for retrieval augmented generation. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), vol.\u00a038, pp. 36371\u201336405 (2025). https:\/\/openreview.net\/forum?id=0QNmAvQQqj","DOI":"10.52202\/085713-1222"},{"key":"32_CR57","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: Video-RAG: visually-aligned retrieval-augmented long video comprehension. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), vol.\u00a038, pp. 168008\u2013168033 (2025). https:\/\/openreview.net\/forum?id=QaZxGWlbgO","DOI":"10.52202\/085713-5602"},{"key":"32_CR58","unstructured":"Ma, S., et al.: Think-on-graph 2.0: deep and faithful large language model reasoning with knowledge-guided retrieval augmented generation. In: International Conference on Learning Representations (ICLR). vol.\u00a02025, pp. 52782\u201352806 (2025). https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2025\/file\/830b1abc6d2da85f23d41169fa44d185-Paper-Conference.pdf"},{"key":"32_CR59","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 (ICCV), pp. 3113\u20133124 (2023). https:\/\/openaccess.thecvf.com\/content\/ICCV2023\/html\/Mensink_Encyclopedic_VQA_Visual_Questions_About_Detailed_Properties_of_Fine-Grained_Categories_ICCV_2023_paper.html","DOI":"10.1109\/ICCV51070.2023.00289"},{"key":"32_CR60","doi-asserted-by":"crossref","unstructured":"Methani, N., Ganguly, P., Khapra, M.M., Kumar, P.: PlotQA: reasoning over scientific plots. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1527\u20131536 (2020). https:\/\/openaccess.thecvf.com\/content_WACV_2020\/html\/Methani_PlotQA_Reasoning_over_Scientific_Plots_WACV_2020_paper.html","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"32_CR61","unstructured":"Nussbaum, Z., Morris, J.X., Mulyar, A., Duderstadt, B.: Nomic Embed: Training a Reproducible Long Context Text Embedder. Trans. Mach. Learn. Res. (TMLR) (2025). https:\/\/openreview.net\/forum?id=IPmzyQSiQE"},{"key":"32_CR62","unstructured":"OpenAI Team: Introducing GPT-5.2: The Most Advanced Frontier Model for Professional Work and Long-running Agents (2026). https:\/\/openai.com\/index\/introducing-gpt-5-2\/"},{"key":"32_CR63","unstructured":"Qi, J., et al.: RoRA-VLM: Robust Retrieval-Augmented Vision Language Models. arXiv preprint arXiv:2410.08876 (2024). https:\/\/arxiv.org\/abs\/2410.08876"},{"key":"32_CR64","unstructured":"Qwen Team: Qwen3.5: Towards Native Multimodal Agents (2026). https:\/\/qwen.ai\/blog?id=qwen3.5"},{"key":"32_CR65","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning (ICML), pp. 8748\u20138763 (2021). https:\/\/proceedings.mlr.press\/v139\/radford21a"},{"key":"32_CR66","unstructured":"Sarthi, P., Abdullah, S., Tuli, A., Khanna, S., Goldie, A., Manning, C.D.: RAPTOR: recursive abstractive processing for tree-organized retrieval. In: The Twelfth International Conference on Learning Representations (ICLR). vol.\u00a02024, pp. 32628\u201332649 (2024). https:\/\/openreview.net\/forum?id=GN921JHCRw"},{"key":"32_CR67","unstructured":"Sun, J., et al.: Think-on-graph: deep and responsible reasoning of large language model on knowledge graph. In: The Twelfth International Conference on Learning Representations (ICLR), vol.\u00a02024, pp. 3868\u20133898 (2024). https:\/\/openreview.net\/forum?id=nnVO1PvbTv"},{"key":"32_CR68","unstructured":"Sun, Q., et al.: EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters. arXiv preprint arXiv:2402.04252 (2024). https:\/\/arxiv.org\/abs\/2402.04252"},{"key":"32_CR69","unstructured":"Wan, X., Yu, H.: MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs. arXiv preprint arXiv:2507.20804 (2025). https:\/\/arxiv.org\/abs\/2507.20804"},{"key":"32_CR70","unstructured":"Wang, L., Chen, H., Yang, N., Huang, X., Dou, Z., Wei, F.: Chain-of-retrieval augmented generation. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), pp. 59888\u201359915 (2025). https:\/\/openreview.net\/forum?id=gUPGGCM4WH"},{"key":"32_CR71","doi-asserted-by":"crossref","unstructured":"Wang, S., Fang, Y., Zhou, Y., Liu, X., Ma, Y.: ArchRAG: attributed community-based hierarchical retrieval-augmented generation. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 15868\u201315876 (2026). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38619","DOI":"10.1609\/aaai.v40i19.38619"},{"key":"32_CR72","doi-asserted-by":"crossref","unstructured":"Wasserman, N., et al.: Real-mm-rag: A real-world multi-modal retrieval benchmark. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 31660\u201331683 (2025). https:\/\/aclanthology.org\/2025.acl-long.1528\/","DOI":"10.18653\/v1\/2025.acl-long.1528"},{"key":"32_CR73","doi-asserted-by":"crossref","unstructured":"Wu, J., Zhu, J., Liu, Y., Xu, M., Jin, Y.: Agentic reasoning: a streamlined framework for enhancing LLM reasoning with agentic tools. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 28489\u201328503 (2025). https:\/\/aclanthology.org\/2025.acl-long.1383\/","DOI":"10.18653\/v1\/2025.acl-long.1383"},{"key":"32_CR74","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). https:\/\/aclanthology.org\/2024.findings-emnlp.83\/","DOI":"10.18653\/v1\/2024.findings-emnlp.83"},{"key":"32_CR75","unstructured":"Yasunaga, M., et al.: Retrieval-Augmented Multimodal Language Modeling, pp. 39755\u201339769 (2022). https:\/\/proceedings.mlr.press\/v202\/yasunaga23a.html"},{"key":"32_CR76","unstructured":"You, X., Huang, Q., Li, L., Chang, X., Yu, J.: Cut to the chase: training-free multimodal summarization via chain-of-events. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26219\u201326229 (2026). https:\/\/openaccess.thecvf.com\/content\/CVPR2026\/html\/You_Cut_to_the_Chase_Training-free_Multimodal_Summarization_via_Chain-of-Events_CVPR_2026_paper.html"},{"key":"32_CR77","doi-asserted-by":"crossref","unstructured":"You, X., et al.: Knowledge completes the vision: a multimodal entity-aware retrieval-augmented generation framework for news image captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol.\u00a040, pp. 12108\u201312116 (2026). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38200","DOI":"10.1609\/aaai.v40i14.38200"},{"key":"32_CR78","unstructured":"Yu, J., Liu, Y., Gu, J., Torr, P., Zhou, D.: Can knowledge-graph-based retrieval augmented generation really retrieve what you need? In: Proceedings of the Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), vol.\u00a038, pp. 95653\u201395682 (2025). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2025\/file\/89d0d5c2f720921df93bbb8fef514571-Paper-Conference.pdf"},{"key":"32_CR79","doi-asserted-by":"crossref","unstructured":"Yuan, X., Ning, L., Fan, W., Li, Q.: mKG-RAG: multimodal knowledge graph-enhanced RAG for visual question answering. In: Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (2026). https:\/\/doi.org\/10.1145\/3805712.3809680","DOI":"10.1145\/3805712.3809680"},{"key":"32_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Subgraph retrieval enhanced model for multi-hop knowledge base question answering. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (ACL), pp. 5773\u20135784 (2022). https:\/\/aclanthology.org\/2022.acl-long.396\/","DOI":"10.18653\/v1\/2022.acl-long.396"},{"key":"32_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: A comprehensive survey on multimodal RAG: all combinations of modalities as input and output. Authorea Preprints (2025). https:\/\/www.techrxiv.org\/doi\/full\/10.36227\/techrxiv.176341513.38473003","DOI":"10.36227\/techrxiv.176341513.38473003\/v1"},{"key":"32_CR82","unstructured":"Zhang, T., et al.: mR$$^2$$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA. arXiv preprint arXiv:2502.01113 (2024). https:\/\/arxiv.org\/abs\/2411.15041"},{"key":"32_CR83","unstructured":"Zhang, Z., Feng, Y., Zhang, M.: LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers. arXiv preprint arXiv:2502.18139 (2025). https:\/\/arxiv.org\/abs\/2502.18139"},{"key":"32_CR84","doi-asserted-by":"crossref","unstructured":"Zhao, D., Huang, Q., Yan, D., Sun, Y., Yu, J.: Partially shared concept bottleneck models. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol.\u00a040, pp. 13117\u201313125 (2026). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38312","DOI":"10.1609\/aaai.v40i15.38312"},{"key":"32_CR85","unstructured":"Zhao, Y., Zhu, J., Guo, Y., He, K., Li, X.: E$$^2$$GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness. arXiv preprint arXiv:2505.24226 (2025). https:\/\/arxiv.org\/abs\/2505.24226"},{"key":"32_CR86","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: Are they the same? Exploring visual correspondence shortcomings of multimodal LLMs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 17663\u201317674 (2025). https:\/\/openaccess.thecvf.com\/content\/ICCV2025\/html\/Zhou_Are_They_the_Same_Exploring_Visual_Correspondence_Shortcomings_of_Multimodal_ICCV_2025_paper.html","DOI":"10.1109\/ICCV51701.2025.01641"},{"key":"32_CR87","unstructured":"Zhuang, L., et al.: LinearRAG: linear graph retrieval augmented generation on large-scale corpora. In: The Fourteenth International Conference on Learning Representations (2026). https:\/\/openreview.net\/forum?id=mCtfkypdm6"}],"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\/978-3-032-37167-6_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T08:50:19Z","timestamp":1789116619000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37167-6_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371669","9783032371676"],"references-count":87,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37167-6_32","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":"12 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"}}]}}