{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T12:00:10Z","timestamp":1780401610353,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819561957","type":"print"},{"value":"9789819561964","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\/978-981-95-6196-4_11","type":"book-chapter","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T05:59:22Z","timestamp":1770184762000},"page":"153-165","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Dynamic Orchestration of Multi-agent System for Real-World Multi-image Agricultural VQA"],"prefix":"10.1007","author":[{"given":"Yan","family":"Ke","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heming","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott","family":"Chapman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"key":"11_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"11_CR2","unstructured":"Anthropic: Introducing the next generation of claude (2024). http:\/\/anthropic.com\/news\/claude-3-family. Accessed 10 Apr 2025"},{"key":"11_CR3","unstructured":"Bai, S., et al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"11_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR5","unstructured":"Chase, H.: Langchain (2022). https:\/\/github.com\/langchain-ai\/langchain"},{"key":"11_CR6","unstructured":"Chen, Z., et al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)"},{"key":"11_CR7","unstructured":"Chen, Z., et al.: An adaptive framework for generating systematic explanatory answer in online Q &A platforms. arXiv preprint arXiv:2410.17694 (2024)"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"11_CR9","unstructured":"Gauba, A., Pi, I., Man, Y., Pang, Z., Adve, V.S., Wang, Y.X.: Agmmu: a comprehensive agricultural multimodal understanding benchmark (2025). arxiv.org\/abs\/2504.10568"},{"key":"11_CR10","unstructured":"Gravitas, S.: Autogpt (2023). http:\/\/agpt.co\/"},{"key":"11_CR11","unstructured":"Hong, S., et al.: Metagpt: meta programming for a multi-agent collaborative framework. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Koopman, B., et al.: Agask: an agent to help answer farmer\u2019s questions from scientific documents. Int. J. Digit. Libr. 25(4), 569\u2013584 (2024)","DOI":"10.1007\/s00799-023-00369-y"},{"key":"11_CR14","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9459\u20139474 (2020)"},{"key":"11_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":"11_CR16","doi-asserted-by":"crossref","unstructured":"Lin, B., Zhu, B., Ye, Y., Ning, M., Jin, P., Yuan, L.: Video-llava: learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122 (2023)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"11_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2021.106378","volume":"189","author":"C Liu","year":"2021","unstructured":"Liu, C., Zhu, H., Guo, W., Han, X., Chen, C., Wu, H.: EFDet: an efficient detection method for cucumber disease under natural complex environments. Comput. Electron. Agric. 189, 106378 (2021)","journal-title":"Comput. Electron. Agric."},{"issue":"1","key":"11_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3546872","volume":"14","author":"H Liu","year":"2022","unstructured":"Liu, H., et al.: Trustworthy AI: a computational perspective. ACM Trans. Intell. Syst. Technol. 14(1), 1\u201359 (2022)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"11_CR19","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, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"11_CR20","first-page":"34892","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR21","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"11_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108180","volume":"213","author":"MZU Rehman","year":"2023","unstructured":"Rehman, M.Z.U., Raghuvanshi, D., Kumar, N.: Kisanqrs: a deep learning-based automated query-response system for agricultural decision-making. Comput. Electron. Agric. 213, 108180 (2023)","journal-title":"Comput. Electron. Agric."},{"key":"11_CR23","unstructured":"Sharma, S., et al.: Retrieval augmented generation for domain-specific question answering. arXiv preprint arXiv:2404.14760 (2024)"},{"key":"11_CR24","first-page":"69700","volume":"37","author":"X Shen","year":"2024","unstructured":"Shen, X., et al.: MM-WLAuslan: multi-view multi-modal word-level Australian sign language recognition dataset. Adv. Neural. Inf. Process. Syst. 37, 69700\u201369715 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Shiri, F., Guo, X.Y., Far, M.G., Yu, X., Haffari, G., Li, Y.F.: An empirical analysis on spatial reasoning capabilities of large multimodal models. arXiv preprint arXiv:2411.06048 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.1195"},{"key":"11_CR26","unstructured":"Silva, B., Nunes, L., Estev\u00e3o, R., Aski, V., Chandra, R.: GPT-4 as an agronomist assistant? Answering agriculture exams using large language models. arXiv preprint arXiv:2310.06225 (2023)"},{"key":"11_CR27","unstructured":"Georgiev, P., et al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)"},{"key":"11_CR28","unstructured":"Wang, F., et al.: Muirbench: a comprehensive benchmark for robust multi-image understanding. arXiv preprint arXiv:2406.09411 (2024)"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Wei, T., Chen, Z., Yu, X.: Snap and diagnose: an advanced multimodal retrieval system for identifying plant diseases in the wild (2024). arxiv.org\/abs\/2408.14723","DOI":"10.1145\/3696409.3700293"},{"key":"11_CR30","unstructured":"Wu, Q., et al.: Autogen: enabling next-gen LLM applications via multi-agent conversations. In: First Conference on Language Modeling (2024)"},{"issue":"7","key":"11_CR31","doi-asserted-by":"publisher","first-page":"3850","DOI":"10.3390\/app15073850","volume":"15","author":"J Xiong","year":"2025","unstructured":"Xiong, J., Pan, L., Liu, Y., Zhu, L., Zhang, L., Tan, S.: Enhancing plant protection knowledge with large language models: a fine-tuned question-answering system using lora. Appl. Sci. 15(7), 3850 (2025)","journal-title":"Appl. Sci."},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Shizishangpt: an agricultural large language model integrating tools and resources. In: International Conference on Web Information Systems Engineering, pp. 284\u2013298. Springer (2024)","DOI":"10.1007\/978-981-96-0573-6_21"},{"key":"11_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.resconrec.2024.107497","volume":"204","author":"T Yang","year":"2024","unstructured":"Yang, T., Mei, Y., Xu, L., Yu, H., Chen, Y.: Application of question answering systems for intelligent agriculture production and sustainable management: a review. Resour. Conserv. Recycl. 204, 107497 (2024)","journal-title":"Resour. Conserv. Recycl."},{"key":"11_CR34","unstructured":"Zaremehrjerdi, H., et al.: Towards large reasoning models for agriculture. arXiv preprint arXiv:2505.19259 (2025)"},{"key":"11_CR35","first-page":"52670","volume":"37","author":"H Zhang","year":"2024","unstructured":"Zhang, H., et al.: Empowering and assessing the utility of large language models in crop science. Adv. Neural. Inf. Process. Syst. 37, 52670\u201352722 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR36","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with MT-bench and chatbot arena (2023)"}],"container-title":["Lecture Notes in Computer Science","Databases Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6196-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T05:59:31Z","timestamp":1770184771000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6196-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819561957","9789819561964"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6196-4_11","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":"5 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Database Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"4 December 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 December 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"36","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adc-conference.github.io\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}