{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T06:28:21Z","timestamp":1786429701847,"version":"build-2736575974"},"reference-count":64,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006013","name":"United Arab Emirates University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:p>Accurate crop disease diagnosis is critical for agricultural productivity and food security, yet existing deep learning systems often struggle to generalize across visually similar diseases and varying environmental conditions. Recent Vision-Language Models (VLMs) have demonstrated promising zero-shot reasoning capabilities; however, most agricultural diagnostic systems still rely on isolated single-model predictions without collaborative reasoning or consensus mechanisms. In this work, we propose VIDA+PANDA, a multi-agent Vision-Language framework for zero-shot crop disease diagnosis. The framework consists of two stages: VIDA, where multiple VLM agents independently analyze crop leaf images to establish baseline performance, and the Peer-Anchored Named Deliberation Architecture (PANDA), which introduces a structured multi-round debate among a selected group of high-performing and architecturally diverse agents. During deliberation, agents exchange reasoning, critique peer predictions, and revise decisions through evidence-grounded discussion, while an anti-sycophancy mechanism discourages unsupported consensus shifts. Final predictions are generated through performance-weighted consensus voting. Experiments are conducted on the CDDM benchmark using seven heterogeneous VLMs from four independent providers, including two open-source models, under a fully zero-shot setting. A non-participant GPT-5 model serves as an independent judge to assess the final diagnostic predictions. Beyond conventional accuracy, the framework introduces three semantic measures: Semantic Label Similarity (SLS), which measures how semantically close a predicted crop-disease pair is to the ground truth and captures partial correctness overlooked by exact-match evaluation; Reasoning Specificity (RS), which measures how concretely an agent\u2019s explanation references visual evidence such as lesion color, shape, texture, or margins; and Inter-Agent Reasoning Convergence (IRC), which measures the extent to which agents rely on similar visual evidence, capturing epistemic alignment independently of label correctness. Experimental results show that collaborative multiagent deliberation improves individual diagnostic performance and semantic alignment, with the largest gains observed among weaker participating agents. The findings also reveal important relationships between predictive accuracy, persuasive influence, and consensus formation in VLM-based agricultural diagnosis.<\/jats:p>","DOI":"10.3389\/fpls.2026.1890016","type":"journal-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T05:40:21Z","timestamp":1786426821000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A multi-agent vision-language debate framework for zero-shot crop disease diagnosis"],"prefix":"10.3389","volume":"17","author":[{"given":"Mustafa Al","family":"Juboori","sequence":"first","affiliation":[{"name":"College of Information Technology, United Arab Emirates University","place":["Al-Ain, Abu Dhabi, United Arab Emirates"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeeshan","family":"Abbas","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, College of IT Convergence, Gachon University","place":["Seongnam, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zayed Al","family":"Aghbari","sequence":"additional","affiliation":[{"name":"College of Information Technology, United Arab Emirates University","place":["Al-Ain, Abu Dhabi, United Arab Emirates"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farman","family":"Ullah","sequence":"additional","affiliation":[{"name":"College of Information Technology, United Arab Emirates University","place":["Al-Ain, Abu Dhabi, United Arab Emirates"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mobeen Ur","family":"Rehman","sequence":"additional","affiliation":[{"name":"College of Information Technology, United Arab Emirates University","place":["Al-Ain, Abu Dhabi, United Arab Emirates"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2022.100083","article-title":"A survey on using deep learning techniques for plant disease diagnosis and recommendations for development of appropriate tools","volume":"3","author":"Ahmad","year":"2023","journal-title":"Smart Agric. Technol."},{"key":"B2","first-page":"1","article-title":"Enhancing precision in rice leaf disease detection: A transformer model approach with attention mapping","author":"Ahmed","year":"2024"},{"key":"B3","first-page":"8217","article-title":"Unconstrained open vocabulary image classification: Zero-shot transfer from text to image via clip inversion","author":"Allgeuer","year":"2025"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy14020327","article-title":"Vit-smartagri: vision transformer and smartphone-based plant disease detection for smart agriculture","volume":"14","author":"Barman","year":"2024","journal-title":"Agronomy"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117470","article-title":"Swp-leafnet: A novel multistage approach for plant leaf identification based on deep cnn","volume":"202","author":"Beikmohammadi","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"B6","doi-asserted-by":"publisher","first-page":"3797","DOI":"10.1007\/s12145-024-01339-x","article-title":"An approach based on performer-attention-guided few-shot learning model for plant disease classification","volume":"17","author":"Boulila","year":"2024","journal-title":"Earth Sci. Inf."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110028","article-title":"Integrating reinforcement learning and large language models for crop production process management optimization and control through a new knowledge-based deep learning paradigm","volume":"232","author":"Chen","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B8","doi-asserted-by":"crossref","first-page":"8531","DOI":"10.3390\/s23208531","article-title":"Multispectral plant disease detection with vision transformer\u2013 convolutional neural network hybrid approaches","volume":"23","author":"De Silva","year":"2023","journal-title":"Sensors"},{"key":"B9","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1007\/s12517-024-11993-6","article-title":"Assessment and detection of biotic and abiotic stresses in field crops through remote and proximal sensing techniques\u2014evidence from earlier findings","volume":"17","author":"Dhaliwal","year":"2024","journal-title":"Arabian J. Geosci."},{"key":"B10","article-title":"Adapting vision-language models without labels: A comprehensive survey","author":"Dong","year":"2025","journal-title":"arXiv preprint arXiv:2508.05547"},{"key":"B11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:2010.11929"},{"key":"B12","article-title":"Improving factuality and reasoning in language models through multiagent debate","author":"Du","year":"2023","journal-title":"arXiv preprint arXiv:2305.14325"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11831-026-10582-y","article-title":"A comprehensive review of image segmentation techniques for plant disease detection in precision agriculture: Models, trends, and challenges","author":"Duhan","year":"2026","journal-title":"Arch. Comput. Methods Eng."},{"key":"B14","doi-asserted-by":"publisher","first-page":"159","DOI":"10.21608\/jaiep.2026.459281.1053","article-title":"Deep learning architectures and imaging modalities for plant disease detection: A systematic review","volume":"3","author":"Ewieda","year":"2026","journal-title":"J. Artif. Intell. Eng. Pract."},{"key":"B15","doi-asserted-by":"publisher","first-page":"62281","DOI":"10.1109\/access.2023.3286935","article-title":"Model selection of hybrid feature fusion for coffee leaf disease classification","volume":"11","author":"Faisal","year":"2023","journal-title":"IEEE Access"},{"key":"B16","doi-asserted-by":"publisher","first-page":"18589","DOI":"10.1109\/jiot.2023.3236322","article-title":"Machine-learning-based uav-assisted agricultural information security architecture and intrusion detection","volume":"10","author":"Fu","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eiar.2026.108430","article-title":"Exploring the role of artificial intelligence in achieving sustainable development goals: A systematic review","volume":"120","author":"Gao","year":"2026","journal-title":"Environ. Impact Assess. Rev."},{"key":"B18","article-title":"Agmmu: A comprehensive agricultural multimodal understanding benchmark","volume":"38","author":"Gauba","year":"2026","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B19","first-page":"102778","article-title":"Bioclip 2: Emergent properties from scaling hierarchical contrastive learning","volume":"38","author":"Gu","year":"2026","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B20","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1038\/s43016-021-00335-4","article-title":"Extreme climate events increase risk of global food insecurity and adaptation needs","volume":"2","author":"Hasegawa","year":"2021","journal-title":"Nat. Food"},{"key":"B21","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1146\/annurev-resource-101620-080426","article-title":"Agricultural labor supply","volume":"13","author":"Hill","year":"2021","journal-title":"Annu. Rev. Resource Econ"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113197","article-title":"Knowledge assimilation: Implementing knowledge-guided agricultural large language model","volume":"314","author":"Jiang","year":"2025","journal-title":"Knowledge-Based Syst."},{"key":"B23","doi-asserted-by":"publisher","first-page":"66","DOI":"10.54112\/bbasr.v2024i1.66","article-title":"Global agricultural losses and their causes","volume":"2024","author":"Junaid","year":"2024","journal-title":"Bull. Biol. Allied Sci. Res."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103145","article-title":"Llm-dg: Leveraging large language model for enhanced disease prediction via inter-patient and intra-patient modeling","volume":"121","author":"Kang","year":"2025","journal-title":"Inf. Fusion"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14040661","article-title":"Context-aware tomato leaf disease detection using deep learning in an operational framework","volume":"14","author":"Karimanzira","year":"2025","journal-title":"Electronics"},{"key":"B26","doi-asserted-by":"publisher","first-page":"8749","DOI":"10.1007\/s00521-018-3939-6","article-title":"Plant disease recognition using fractional-order zernike moments and svm classifier","volume":"31","author":"Kaur","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"B27","doi-asserted-by":"publisher","first-page":"2917","DOI":"10.1007\/s10462-023-10595-0","article-title":"A survey of the vision transformers and their cnn-transformer based variants","volume":"56","author":"Khan","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2024.045101","article-title":"A systematic literature review of machine learning and deep learning approaches for spectral image classification in agricultural applications using aerial photography","volume":"78","author":"Khan","year":"2024","journal-title":"Computers Mater. Continua"},{"key":"B29","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1016\/j.matpr.2023.02.370","article-title":"Agricultural plant diseases identification: From traditional approach to deep learning","volume":"80","author":"Kotwal","year":"2023","journal-title":"Mater. Today Proc."},{"key":"B30","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1111\/ppa.14033","article-title":"Climate change and plant pathogens: Understanding dynamics, risks and mitigation strategies","volume":"74","author":"Kumar","year":"2025","journal-title":"Plant Pathol."},{"key":"B31","doi-asserted-by":"publisher","first-page":"5944","DOI":"10.1109\/tase.2024.3434610","article-title":"Grasping with occlusion-aware ally method in complex scenes","volume":"22","author":"Li","year":"2024","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.32388\/gxr68q","article-title":"Benchmark evaluations, applications, and challenges of large vision language models: A survey","volume":"1","author":"Li","year":"2025","journal-title":"arXiv preprint arXiv:2501.02189"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy14081729","article-title":"Pmlpnet: Classifying multi-class pests in wild environment via a novel convolutional neural network","volume":"14","author":"Liu","year":"2024","journal-title":"Agronomy"},{"key":"B34","doi-asserted-by":"publisher","first-page":"192206","DOI":"10.1007\/s11432-024-4289-6","article-title":"A formal model for multiagent q-learning on graphs","volume":"68","author":"Liu","year":"2025","journal-title":"Sci. China Inf. Sci."},{"key":"B35","first-page":"157","article-title":"A multimodal benchmark dataset and model for crop disease diagnosis","author":"Liu","year":"2024"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123643","article-title":"Identification of rice disease under complex background based on psoc-drcnet","volume":"249","author":"Liu","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1111\/jph.13438","article-title":"Flvaegwo-cnn: Grey wolf optimisationbased cnn for classification of olive leaf disease via focal loss variational autoencoder","volume":"172","author":"Majikumna","year":"2024","journal-title":"J. Phytopathol."},{"key":"B38","first-page":"441","article-title":"Application of artificial intelligence and machine learning in agriculture","author":"Marwaha","year":"2023"},{"key":"B39","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s44279-024-00078-3","article-title":"Unlocking the potential of precision agriculture for sustainable farming","volume":"2","author":"Mgendi","year":"2024","journal-title":"Discover Agric."},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106316","article-title":"An automatic classification framework for identifying type of plant leaf diseases using multi-scale feature fusion-based adaptive deep network","volume":"95","author":"Nagachandrika","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1735096","article-title":"Vision-language models for zero-shot weed detection and visual reasoning in uav-based precision agriculture","volume":"16","author":"Nasir","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B42","article-title":"World population prospects 2024: Summary of results. 2024","volume-title":"URL: Https:\/\/Www. Un. Org\/Development\/Desa\/Pd\/Sites\/Www. Un. Org. Development. Desa. Pd\/Files\/Wpp2022 Summary of Results. Pdf","year":"2024"},{"key":"B43","first-page":"9630","article-title":"Agriclip: Adapting clip for agriculture and livestock via domain-specialized cross-model alignment","author":"Nawaz","year":"2025"},{"key":"B44","first-page":"659","article-title":"Maize leaf disease detection and classification using machine learning algorithms","author":"Panigrahi","year":"2020"},{"key":"B45","doi-asserted-by":"publisher","first-page":"e270","DOI":"10.1016\/s2542-5196(24)00021-4","article-title":"Interconnecting global threats: climate change, biodiversity loss, and infectious diseases","volume":"8","author":"Pfenning-Butterworth","year":"2024","journal-title":"Lancet Planet. Heath"},{"key":"B46","article-title":"Leafnet: A large-scale dataset and comprehensive benchmark for foundational vision-language understanding of plant diseases","author":"Quoc","year":"2026","journal-title":"arXiv preprint arXiv:2602.13662"},{"key":"B47","doi-asserted-by":"publisher","first-page":"130084","DOI":"10.36227\/techrxiv.174062971.11176782\/v1","article-title":"A vision-language foundation model for leaf disease identification","author":"Quoc","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B48","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1109\/tafe.2023.3329849","article-title":"A review on plant disease detection using hyperspectral imaging","volume":"1","author":"Rayhana","year":"2023","journal-title":"IEEE Trans. Agrifood Electron."},{"key":"B49","doi-asserted-by":"crossref","DOI":"10.1051\/itmconf\/20224403049","article-title":"Plant disease detection using cnn","author":"Shelar","year":"2022"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103158","article-title":"Uavs meet llms: Overviews and perspectives towards agentic low-altitude mobility","volume":"122","author":"Tian","year":"2025","journal-title":"Inf. Fusion"},{"key":"B51","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/s10462-024-11100-x","article-title":"Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture","volume":"58","author":"Upadhyay","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"B52","doi-asserted-by":"crossref","DOI":"10.1561\/116.20240058","article-title":"Yolov1 to yolov10: The fastest and most accurate real-time object detection systems","volume-title":"Arxiv Preprint Arxiv:2408.09332","author":"Wang","year":"2024"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2024.102820","article-title":"Knowledge graph of agricultural engineering technology based on large language model","volume":"85","author":"Wang","year":"2024","journal-title":"Displays"},{"key":"B54","doi-asserted-by":"publisher","first-page":"111010","DOI":"10.2139\/ssrn.5066530","article-title":"Ct-hiffnet: A contourtexture hierarchical feature fusion network for cropland field parcel extraction from high-resolution remote sensing images","volume":"239","author":"Wu","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B55","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.5731427","article-title":"Rethinking hallucinations: A cognitive-inspired taxonomy and comprehensive survey in large language models, large vision-language models, and multimodal large language models","volume-title":"Large Vision-Language Models, and Multimodal Large Language Models (November 09, 2025)","author":"Xia","year":"2025"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2024.114970","article-title":"Esmnet: An enhanced yolov7-based approach to detect surface defects in precision metal workpieces","volume":"235","author":"Xu","year":"2024","journal-title":"Measurement"},{"key":"B57","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/s11227-025-07135-8","article-title":"A vision-based inspection system for pharmaceutical production line","volume":"81","author":"Xu","year":"2025","journal-title":"J. Supercomputing"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1109\/tci.2025.3598440","article-title":"Towards multi-source illumination color constancy through physics-based rendering and spectral power distribution embedding","author":"Xue","year":"2025","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3661417","article-title":"Pestscope: Exclusion-aware large multimodal model for fine-grained agricultural pest segmentation","author":"Yang","year":"2026","journal-title":"IEEE Trans. Image Process"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.1126\/science.adn3747","article-title":"Climate change exacerbates the environmental impacts of agriculture","volume":"385","author":"Yang","year":"2024","journal-title":"Science"},{"key":"B61","doi-asserted-by":"publisher","first-page":"14","DOI":"10.47760\/ijcsmc.2021.v10i01.003","article-title":"Ensemble classifier for plant disease detection","volume":"10","author":"Yousuf","year":"2021","journal-title":"Int. J. Comput. Sci. Mobile Computing"},{"key":"B62","doi-asserted-by":"publisher","first-page":"4396","DOI":"10.1109\/tpami.2022.3195549","article-title":"Domain generalization: A survey","volume":"45","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1579355","article-title":"Harnessing large vision and language models in agriculture: A review","volume":"16","author":"Zhu","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B64","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127924","article-title":"Gcstormer: Gated swin transformer with channel weights for image denoising","volume":"284","author":"Zhu","year":"2025","journal-title":"Expert Syst. Appl."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1890016\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T05:40:23Z","timestamp":1786426823000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1890016\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":64,"alternative-id":["10.3389\/fpls.2026.1890016"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1890016","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,11]]},"article-number":"1890016"}}