Agroecology; Artificial intelligence; Large language models; Pesticide reduction; Evidence synthesis; Biological control; Chatbot; Systematic literature review
Abstract :
[en] Generative artificial intelligence (AI) could transform evidence synthesis and revolutionize the global scientific enterprise, yet its agricultural applications are understudied. Here, we systematically assess the performance of three web-grounded AI engines (ChatGPT, ScholarAI and DeepSeek) in synthesizing the global literature on biological control of the fall armyworm Spodoptera frugiperda, and benchmark their outputs against a recent, near-exhaustive human review. Though all engines rapidly screened vast literature corpora, they exhibited shortcomings in factual accuracy, reporting reliability and data consistency. In machine-run syntheses, natural enemy prevalence and performance data often diverged from published records while the level of agreement in enumerating top-performing taxa was evenly low. Meanwhile, internal consistency between laboratory and field-level parasitism data for ScholarAI and DeepSeek was similar to that in human-run reviews. All models tended towards faulty data extrapolation, hallucination and data fabrication, and a sporadic exclusion of key species. While autonomous, machine-only efforts accurately capture coarse-grained patterns in natural enemy identity, abundance, and impacts, they carry limited utility for (living) evidence syntheses or rigorous decision-support. Yet, handled with prudence and due human oversight, machine power might eventually revitalize underfunded disciplines and advance nature-friendly farming.
Disciplines :
Agriculture & agronomy
Author, co-author :
Wyckhuys, Kris A.G. ; Chrysalis Consulting, Danang, Viet Nam ; Institute for Plant Protection, China Academy of Agricultural Sciences (CAAS), Beijing, China ; School of the Environment, University of Queensland, Saint Lucia, Australia ; Food and Agriculture Organization (FAO), Bangkok, Thailand
Akutse, Komivi S.; International Centre of Insect Physiology and Ecology (icipe), Nairobi, Kenya ; Unit for Environmental Sciences and Management, North-West University, Potchefstroom, South Africa
Amalin, Divina M.; Institute of Biological Control, De La Salle University, Manila, Philippines
Araj, Salah-Eddin; School of Agriculture, The University of Jordan, Amman, Jordan
Beltran, Marie Joy B.; National Crop Protection Center, University of the Philippines Los Baños, Laguna, Philippines
Ben Fekih, Ibtissem ; Université de Liège - ULiège > Département GxABT > Gestion durable des bio-agresseurs
Calatayud, Paul-André; International Centre of Insect Physiology and Ecology (icipe), Nairobi, Kenya ; Institut Diversité Ecologie et Evolution du Vivant (IDEEV), Université Paris-Saclay, CNRS, IRD, UMR Evolution, Génomes, Comportement et Ecologie, Gif‑sur‑Yvette, France
Cicero, Lizette; Instituto Nacional de Investigaciones Forestales, Agrícolas y Pecuarias (INIFAP), Yucatán, Mexico
Cokola, Marcellin C.; Functional and Evolutionary Entomology, Gembloux Agro-Bio Tech, University of Liege, Gembloux, Belgium
Colmenarez, Yelitza C.; CAB International Latin America, FEPAF-UNESP-FCA. Fazenda Exp. Lageado. Botucatu, São Paulo, Brazil
Fernández-Triana, José L.; Canadian National Collection of Insects, Arachnids and Nematodes, Agriculture and Agri-Food Canada, Ottawa, Canada
Francis, Frédéric ; Université de Liège - ULiège > Département GxABT > Gestion durable des bio-agresseurs
Haddi, Khalid; Laboratory of Conservation Biological Control, Department of Entomology, Universidade Federal de Lavras, Brazil
Harrison, Rhett D.; CIFOR-ICRAF, Lusaka, Zambia
Haseeb, Muhammad; Center for Biological Control, Florida A&M University, Tallahassee, United States
Iwanicki, Natasha S.A.; Luiz de Queiroz College of Agriculture, University of São Paulo, Piracicaba, Brazil
Jaber, Lara R.; School of Agriculture, The University of Jordan, Amman, Jordan
Khamis, Fathiya M.; International Centre of Insect Physiology and Ecology (icipe), Nairobi, Kenya
Legaspi, Jesusa C.; United States Department of Agriculture-Agricultural Research Service (USDA-ARS), Center for Medical, Agricultural and Medical Entomology, Tallahassee, United States
Lomeli-Flores, Refugio J.; Posgrado en Fitosanidad, Colegio de Postgraduados, Texcoco, Mexico
Lyu, Baoqian; Environment and Plant Protection Institute, Chinese Academy of Tropical Agricultural Sciences, Haikou, China
Montoya-Lerma, James; Department of Biology, Universidad del Valle, Cali, Colombia
Nurkomar, Ihsan; Universitas Muhammadiyah Yogyakarta, Indonesia
O'Hara, James E.; Canadian National Collection of Insects, Arachnids and Nematodes, Agriculture and Agri-Food Canada, Ottawa, Canada
Perier, Jermaine D.; University of Georgia, Tifton, United States
Ramírez-Romero, Ricardo; Biological Control Laboratory (LabCB-AIFEN), University of Guadalajara, Guadalajara, Mexico
Sanchez-Garcia, Francisco J.; Murcia, Spain
Robinson-Baker, Ann Marie S.; Center for Biological Control, Florida A&M University, Tallahassee, United States
Silveira, Luis C.P.; Laboratory of Conservation Biological Control, Department of Entomology, Universidade Federal de Lavras, Brazil
Simeon, Larisner; Center for Biological Control, Florida A&M University, Tallahassee, United States
Solter, Leellen F.; Illinois Natural History Survey, Prairie Research Institute, University of Illinois, Champaign, United States
Santos-Amaya, Oscar F.; Universidad of Pamplona, Pamplona, Colombia
de Souza Tavares, Wagner; Riau Andalan Pulp and Paper (RAPP), Riau, Indonesia
Abbas, A., Ullah, F., Hafeez, M., Han, X., Dara, M.Z.N., et al. Biological control of fall armyworm, Spodoptera Frugiperda. Agronomy, 12(11), 2022, 2704.
Anonymous, 2024. China has become a scientific superpower. https://www.economist.com/science-and-technology/2024/06/12/china-has-become-a-scientific-superpower, accessed on August 20, 2025.
Baidoo-Anu, D., Ansah, L.O., Education in the era of generative artificial intelligence (AI): understanding the potential benefits of ChatGPT in promoting teaching and learning. J. AI 7:1 (2023), 52–62.
Bolaños, F., Salatino, A., Osborne, F., Motta, E., Artificial intelligence for literature reviews: opportunities and challenges. Artif. Intell. Rev., 57(10), 2024, 259.
Bommasani, R., Hudson, D.A., Adeli, E., Altman, R., Arora, S., et al., 2021. On the opportunities and risks of foundation models. arXiv 2021. arXiv preprint arXiv:2108.07258.
Bradicich, P.A., Faris, A.M., Gordy, J.W., Brewer, M.J., Natural increases in parasitoid and predator abundances and a shift in species dominance point to improved suppression of the sorghum aphid since its invasion into North America. Insects, 15(12), 2024, 958.
Calone, R., Raparelli, E., Bajocco, S., Rossi, E., Crecco, L., et al. Analysing the potential of ChatGPT to support plant disease risk forecasting systems. Smart Agric. Technol., 10, 2025, 100824.
Casas, J., Swarbrick, S., Murdoch, W.W., Parasitoid behaviour: predicting field from laboratory. Ecol. Entomol. 29:6 (2004), 657–665.
Chen, H., Jiang, Z., Liu, X., Xue, C.C., Yew, S.M.E., et al. Can large language models fully automate or partially assist paper selection in systematic reviews?. Br. J. Ophthalmol., 2025 in press.
Clark, J., Barton, B., Albarqouni, L., Byambasuren, O., Jowsey, T., et al. Generative artificial intelligence use in evidence synthesis: a systematic review. Res. Synth. Methods, 2025, 1–19.
Conroy, G., Mallapaty, S., How China created AI model DeepSeek and shocked the world. Nature 638 (2025), 300–301.
Daily, G.C., Polasky, S., Goldstein, J., Kareiva, P.M., Mooney, H.A., et al. Ecosystem services in decision making: time to deliver. Front. Ecol. Environ. 7:1 (2009), 21–28.
De Clercq, D., Nehring, E., Mayne, H., Mahdi, A., Large language models can help boost food production, but be mindful of their risks. Front. Artif. Intell., 7, 2024, 1326153.
EC, 2021. Evaluating the impact of nature-based solutions – A summary for policy makers. European Commission: Directorate-General for Research and Innovation (DG RTD). Publications Office, Brussels, Belgium.
Elliott, J.H., Synnot, A., Turner, T., Simmonds, M., Akl, E.A., et al. Living systematic review: 1. Introduction—the why, what, when, and how. J. Clin. Epidemiol. 91 (2017), 23–30.
Emsley, R., ChatGPT: these are not hallucinations–they're fabrications and falsifications. Schizophrenia, 9(1), 2023, 52.
Gibney, E., China's cheap, open AI model DeepSeek thrills scientists. Nature 638 (2025), 13–14.
Gartlehner, G., Affengruber, L., Titscher, V., Noel-Storr, A., Dooley, G., et al. Single-reviewer abstract screening missed 13 percent of relevant studies: a crowdbased, randomized controlled trial. J. Clin. Epidemiol. 121 (2020), 20–28.
Gladstone, S.H., Parasitos del cogollero, Spodoptera frugiperda Smith (Lepidoptra: Noctuidae) en maiz sembrado en la epoca seca en Nicaragua. Ceiba 32:2 (1991), 201–206.
Gohr, C., Rodríguez, G., Belomestnykh, S., Berg-Moelleken, D., Chauhan, N., et al. Artificial intelligence in sustainable development research. Nat. Sustainability 8 (2025), 970–978.
González-Chang, M., Wratten, S.D., Shields, M.W., Costanza, R., Dainese, M., et al. Understanding the pathways from biodiversity to agro-ecological outcomes: a new, interactive approach. Agr. Ecosyst. Environ., 301, 2020, 107053.
González-Maldonado, M.B., Correa-Ramírez, M.M., Rosas-García, N.M., Chaírez-Hernández, I., Garzón-Zuñiga, M.A., Genetic variability of species of the genus Meteorus Haliday, 18351, at Durango, Mexico. Southwestern Entomologist 44:4 (2019), 909–918.
Guo, H.F., Fang, J.C., Zhong, W.F., Liu, B.S., Interactions between Meteorus pulchricornis and Spodoptera exigua multiple nucleopolyhedrovirus. J. Insect Sci., 13(1), 2013, 12.
Gupta, S., Ranjan, R. and Singh, S.N., 2024. A comprehensive survey of retrieval-augmented generation (rag): Evolution, current landscape and future directions. arXiv preprint arXiv:2410.12837.
Gurr, G.M., Liu, J., Pogrebna, G., Harnessing artificial intelligence for analysing the impacts of nectar and pollen feeding in conservation biological control. Curr. Opin. Insect Sci., 62, 2024, 101176.
Hanson, M.A., Barreiro, P.G., Crosetto, P., Brockington, D., The strain on scientific publishing. Quant. Sci. Stud. 5:4 (2024), 823–843.
Hoelmer, K.A., Kirk, A.A., Selecting arthropod biological control agents against arthropod pests: can the science be improved to decrease the risk of releasing ineffective agents?. Biol. Control 34:3 (2005), 255–264.
Janssen, A., van Rijn, P.C., Pesticides do not significantly reduce arthropod pest densities in the presence of natural enemies. Ecol. Lett. 24:9 (2021), 2010–2024.
Jara-Chiquito, J.L., Oliva, F., Lobato-Vila, I., Pujade-Villar, J., Temporal changes in the composition of parasitoid assemblages associated with the invasive chestnut gall wasp. Ecol. Entomol. 49:6 (2024), 779–797.
Jin, I., Tangsrivimol, J.A., Darzi, E., Hassan Virk, H.U., Wang, Z., et al. DeepSeek vs. ChatGPT: prospects and challenges. Front. Artif. Intell., 8, 2025, 1576992.
Joos, L., Keim, D.A., Fischer, M.T., 2024. Cutting through the clutter: the potential of LLMs for efficient filtration in systematic literature reviews. arXiv preprint arXiv:2407.10652.
Kacena, M.A., Plotkin, L.I., Fehrenbacher, J.C., The use of artificial intelligence in writing scientific review articles. Curr. Osteoporos. Rep. 22:1 (2024), 115–121.
Kargupta, P., Zhang, N., Zhang, Y., Zhang, R., Mitra, P., Han, J., 2025. TaxoAdapt: aligning LLM-based multidimensional taxonomy construction to evolving research corpora. arXiv preprint arXiv:2506.10737.
Kaygisiz, Ö.F., Teke, M.T., Can deepseek and ChatGPT be used in the diagnosis of oral pathologies?. BMC Oral Health, 25(1), 2025, 638.
Kenis, M., Prospects for classical biological control of Spodoptera frugiperda (Lepidoptera: Noctuidae) in invaded areas using parasitoids from the Americas. J. Econ. Entomol. 116:2 (2023), 331–341.
Kenis, M., Benelli, G., Biondi, A., Calatayud, P.A., Day, R., et al. Invasiveness, biology, ecology, and management of the fall armyworm, Spodoptera Frugiperda. Entomologia Generalis, 43(2), 2023, 187.
Khraisha, Q., Put, S., Kappenberg, J., Warraitch, A., Hadfield, K., Can large language models replace humans in systematic reviews? evaluating GPT‐4's efficacy in screening and extracting data from peer‐reviewed and grey literature in multiple languages. Res. Synth. Methods 15:4 (2024), 616–626.
Kung, T.H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., et al. Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLOS Digital Health, 2(2), 2023, e0000198.
Lamanna, M., Muca, E., Giannone, C., Bovo, M., Boffo, F., Romanzin, A., Cavallini, D., Artificial intelligence meets dairy cow research: Large language model's application in extracting daily time-activity budget data for a meta-analytical study. J. Dairy Sci., 2025 in press.
Luo, P.W., Liu, J.W., Xie, X., Jiang, J.W., Huo, X.Y., et al. DeepSeek vs ChatGPT: a comparison study of their performance in answering prostate cancer radiotherapy questions in multiple languages. Am. J. Clin. Exp. Urol., 13(2), 2025, 176.
Molina-Ochoa, J., Carpenter, J.E., Heinrichs, E.A., Foster, J.E., Parasitoids and parasites of Spodoptera frugiperda (Lepidoptera: Noctuidae) in the Americas and Caribbean Basin: an inventory. Fla. Entomol. 86:3 (2003), 254–289.
Mostafapour, M., Fortier, J.H., Pacheco, K., Murray, H., Garber, G., Evaluating literature reviews conducted by humans versus ChatGPT: comparative study. Jmir AI, 3, 2024, e56537.
Nguyen, D.H., Nakai, M., Takatsuka, J., Okuno, S., Ishii, T., et al. Interaction between a nucleopolyhedrovirus and the braconid parasitoid Meteorus pulchricornis (Hymenoptera: Braconidae) in the larvae of Spodoptera litura (Lepidoptera: Noctuidae). Appl. Entomol. Zool. 40:2 (2005), 325–334.
Normile, D., Chinese firm's large language model makes a splash. Science, 387, 2025, 238.
Oerke, E.C., Crop losses to pests. J. Agric. Sci. 144:1 (2006), 31–43.
Pair, S.D., Gross, H.R., Seasonal incidence of fall armyworm (Lepidopera: Noctuidae) pupal parasitism in corn by Diapetimorpha introita and Cryptus albitarsis (Hymenoptera: Ichneumonidae). J. Entomol. Sci. 24:3 (1989), 339–343.
Pavageau, C., Pondini, S. and Geck, M. 2020. Money flows: what is holding back investment in agroecological research for Africa. Biovision Foundation for Ecological Development & International Panel of Experts on Sustainable Food Systems IPES-Food, Zurich, Switzerland.
Pimbert, M.P., Moeller, N.I., Absent agroecology aid: on UK agricultural development assistance since 2010. Sustainability, 10(2), 2018, 505.
Schaffner, U., Heimpel, G.E., Mills, N.J., Muriithi, B.W., Thomas, M.B., et al. Biological control for one health. Sci. Total Environ., 951, 2024, 175800.
Scherbakov, D., Hubig, N., Jansari, V., Bakumenko, A., Lenert, L.A., The emergence of large language models as tools in literature reviews: a large language model-assisted systematic review. J. Am. Med. Inform. Assoc. 32:6 (2025), 1071–1086.
Schneider, K., Barreiro-Hurle, J., Rodriguez-Cerezo, E., Pesticide reduction amidst food and feed security concerns in Europe. Nat. Food 4:9 (2023), 746–750.
Shattuck, A., Werner, M., Mempel, F., Dunivin, Z., Galt, R., Global pesticide use and trade database (GloPUT): New estimates show pesticide use trends in low-income countries substantially underestimated. Glob. Environ. Chang., 81, 2023, 102693.
Shepherd, K.D., Miller, M.A., Kisitu, B., Miles, B.G., Gbedevi, K. et al. 2025. Virtual Agronomist-an AI-assisted chatbot for guiding crop management decisions of smallholder farmers in Africa. agriRxiv, (2025), p.20250269995.
Silva, B., Nunes, L., Esteva, R., Aski, V., Chandra, R., 2023. GPT-4 as an agronomist assistant? Answering agriculture exams using large language models. arXiv [preprint] arXiv.2310.06225. doi: 10.48550/arXiv.2310.06225.
Susnjak, T., Hwang, P., Reyes, N., Barczak, A.L., McIntosh, T., et al. Automating research synthesis with domain-specific large language model fine-tuning. ACM Trans. Knowl. Discov. Data 19:3 (2025), 1–39.
Tambo, J.A., Kansiime, M.K., Mugambi, I., Rwomushana, I., Kenis, M., et al. Understanding smallholders' responses to fall armyworm (Spodoptera frugiperda) invasion: evidence from five african countries. Sci. Total Environ., 740, 2020, 140015.
Tang, F.H., Wyckhuys, K.A.G., Li, Z., Maggi, F., Silva, V., Transboundary impacts of pesticide use in food production. Nat. Rev. Earth & Environ. 6 (2025), 383–400.
Tordjman, M., Liu, Z., Yuce, M., Fauveau, V., et al. Comparative benchmarking of the DeepSeek large language model on medical tasks and clinical reasoning. Nat. Med., 2025, 1.
Turner, T., Lavis, J.N., Grimshaw, J.M., Green, S., Elliott, J., Living evidence and adaptive policy: perfect partners?. Health Research Policy and Systems, 21(1), 2023, 135.
Tzachor, A., Devare, M., Richards, C., Pypers, P., Ghosh, A., et al. Large language models and agricultural extension services. Nat. Food 4:11 (2023), 941–948.
van Dijk, S.H., Brusse-Keizer, M.G., Bucsan, C.C., van der Palen, J., Doggen, C.J., Lenferink, A., Artificial intelligence in systematic reviews: promising when appropriately used. BMJ Open, 13(7), 2023, e072254.
Van Dis, E.A., Bollen, J., Zuidema, W., Van Rooij, R., et al. ChatGPT: five priorities for research. Nature 614:7947 (2023), 224–226.
Van Lenteren, J.C., The state of commercial augmentative biological control: plenty of natural enemies, but a frustrating lack of uptake. BioControl 57:1 (2012), 1–20.
Van Veen, D., Van Uden, C., Blankemeier, L., Delbrouck, J.B., Aali, A., et al. Adapted large language models can outperform medical experts in clinical text summarization. Nat. Med. 30:4 (2024), 1134–1142.
Wyckhuys, K.A.G., Akutse, K.S., Amalin, D.M., Araj, S.E., Barrera, G., et al. Global scientific progress and shortfalls in biological control of the fall armyworm Spodoptera frugiperda. Biol. Control, 191, 2024, 105460.
Wyckhuys, K.A.G., Leatemia, J.A., Fanani, M.Z., Furlong, M.J., Gu, B., et al. Generalist predators shape biotic resistance along a tropical island chain. Plants, 12(18), 2023, 3304.
Wyckhuys, K.A.G., Sanchez-Bayo, F., Aebi, A., Van Lexmond, M.B., Bonmatin, J.M., et al. Stay true to integrated pest management. Science, 371(6525), 2021, 133.
Yang, X., Wyckhuys, K.A.G., Jia, X., Nie, F., Wu, K., Fall armyworm invasion heightens pesticide expenditure among chinese smallholder farmers. J. Environ. Manage., 282, 2021, 111949.
Yang, S., Yuan, Z., Li, S., Peng, R., Liu, K., Yang, P., 2024. Gpt-4 as evaluator: Evaluating large language models on pest management in agriculture. arXiv preprint arXiv:2403.11858.
Ye, A., Maiti, A., Schmidt, M., Pedersen, S.J., A hybrid semi-automated workflow for systematic and literature review processes with large language model analysis. Future Internet, 16(5), 2024, 167.
Yuan, X.T., Shao, C.Y., Zhang, Z.Z., Qian, D., Comparing the performance of ChatGPT and ERNIE Bot in answering questions regarding liver cancer interventional radiology in Chinese and English contexts: a comparative study. Digital Health, 11, 2025, 20552076251315511.
