Articles | Volume 18, issue 15
https://doi.org/10.5194/gmd-18-4983-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-18-4983-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
InsNet-CRAFTY v1.0: integrating institutional network dynamics powered by large language models with land use change simulation
Yongchao Zeng
CORRESPONDING AUTHOR
Institute of Meteorology and Climate Research, Atmospheric Environmental Research (IMK-IFU), Karlsruhe Institute of Technology, 82467 Garmisch-Partenkirchen, Germany
Calum Brown
Institute of Meteorology and Climate Research, Atmospheric Environmental Research (IMK-IFU), Karlsruhe Institute of Technology, 82467 Garmisch-Partenkirchen, Germany
Highlands Rewilding Limited, The Old School House, Bunloit, Drumnadrochit, IV63 6XG, UK
Mohamed Byari
Institute of Meteorology and Climate Research, Atmospheric Environmental Research (IMK-IFU), Karlsruhe Institute of Technology, 82467 Garmisch-Partenkirchen, Germany
Joanna Raymond
Institute of Meteorology and Climate Research, Atmospheric Environmental Research (IMK-IFU), Karlsruhe Institute of Technology, 82467 Garmisch-Partenkirchen, Germany
Thomas Schmitt
Institute of Meteorology and Climate Research, Atmospheric Environmental Research (IMK-IFU), Karlsruhe Institute of Technology, 82467 Garmisch-Partenkirchen, Germany
Mark Rounsevell
Institute of Meteorology and Climate Research, Atmospheric Environmental Research (IMK-IFU), Karlsruhe Institute of Technology, 82467 Garmisch-Partenkirchen, Germany
Institute of Geography and Geo-ecology, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany
School of Geosciences, University of Edinburgh, Drummond Street, Edinburgh, EH8 9XP, UK
Related authors
Yongchao Zeng, Calum Brown, Joanna Raymond, Mohamed Byari, Ronja Hotz, and Mark Rounsevell
Earth Syst. Dynam., 16, 423–449, https://doi.org/10.5194/esd-16-423-2025, https://doi.org/10.5194/esd-16-423-2025, 2025
Short summary
Short summary
This study explores using large language models (LLMs) to simulate policy-making in land systems. We integrated LLMs into a land use model and simulated LLM-powered institutional agents steering meat production by taxation. The results show LLMs can generate boundedly rational policy-making behaviours that can hardly be modelled using conventional methods; LLMs can offer the reasoning behind policy actions. We also discussed LLMs’ potential and challenges in large-scale simulations.
Sophie Reinermann, Carolin Boos, Andrea Kaim, Anne Schucknecht, Sarah Asam, Ursula Gessner, Sylvia H. Annuth, Thomas M. Schmitt, Thomas Koellner, and Ralf Kiese
Biogeosciences, 22, 4969–4992, https://doi.org/10.5194/bg-22-4969-2025, https://doi.org/10.5194/bg-22-4969-2025, 2025
Short summary
Short summary
Grasslands shape the landscape in many parts of the world and serve as the main source of fodder for livestock. There is a lack of comprehensive data on grassland yield, although these data are highly valuable for authorities and research. By applying three approaches to estimate grassland yields, namely, a satellite data model, a biogeochemical model and a field measurements approach, we provide annual grassland yield maps for the Ammer region in 2019 and highlight the potentials and limitations of the approaches.
Yongchao Zeng, Calum Brown, Joanna Raymond, Mohamed Byari, Ronja Hotz, and Mark Rounsevell
Earth Syst. Dynam., 16, 423–449, https://doi.org/10.5194/esd-16-423-2025, https://doi.org/10.5194/esd-16-423-2025, 2025
Short summary
Short summary
This study explores using large language models (LLMs) to simulate policy-making in land systems. We integrated LLMs into a land use model and simulated LLM-powered institutional agents steering meat production by taxation. The results show LLMs can generate boundedly rational policy-making behaviours that can hardly be modelled using conventional methods; LLMs can offer the reasoning behind policy actions. We also discussed LLMs’ potential and challenges in large-scale simulations.
Calum Brown, Ian Holman, and Mark Rounsevell
Earth Syst. Dynam., 12, 211–231, https://doi.org/10.5194/esd-12-211-2021, https://doi.org/10.5194/esd-12-211-2021, 2021
Short summary
Short summary
The variety of human and natural processes in the land system can be modelled in many different ways. However, little is known about how and why basic model assumptions affect model results. We compared two models that represent land use in completely distinct ways and found several results that differed greatly. We identify the main assumptions that caused these differences and therefore key issues that need to be addressed for more robust model development.
Cited articles
Acs, S., Hanley, N., Dallimer, M., Gaston, K. J., Robertson, P., Wilson, P., and Armsworth, P. R.: The effect of decoupling on marginal agricultural systems: implications for farm incomes, land use and upland ecology, Land Use Policy, 27, 550–563, https://doi.org/10.1016/j.landusepol.2009.07.009, 2010.
Ariti, A. T., van Vliet, J., and Verburg, P. H.: The role of institutional actors and their interactions in the land use policy making process in Ethiopia, J. Environ. Manage., 237, 235–246, https://doi.org/10.1016/j.jenvman.2019.02.059, 2019.
Arnott, R., De Palma, A., and Lindsey, R.: Information and time-of-usage decisions in the bottleneck model with stochastic capacity and demand, Eur. Econ. Rev., 43, 525–548, https://doi.org/10.1016/S0014-2921(98)00013-0, 1999.
Bainbridge, A., Troppe, T., and Bartley, J.: Responding to research evidence in Parliament: A case study on selective education policy, Rev. Educ., 10, e3335, https://doi.org/10.1002/rev3.3335, 2022.
Banerjee, S., Agarwal, A., and Singla, S.: Llms will always hallucinate, and we need to live with this, arXiv [preprint], https://doi.org/arXiv:2409.05746, 2024.
Barnett, M. N. and Finnemore, M.: The politics, power, and pathologies of international organizations, Int. Organ., 53, 699–732, https://doi.org/10.1162/002081899551048, 1999.
Broussard, A., Dahdouh-Guebas, F., and Hugé, J.: Diversity of perspectives in biodiversity conservation: A case study of port land use in Antwerp and Rotterdam, J. Environ. Manage., 341, 117937, https://doi.org/10.1016/j.jenvman.2023.117937, 2023.
Brown, C., Seo, B., and Rounsevell, M.: Societal breakdown as an emergent property of large-scale behavioural models of land use change, Earth Syst. Dynam., 10, 809–845, https://doi.org/10.5194/esd-10-809-2019, 2019.
Cairney, P., Heikkila, T., and Wood, M.: Making policy in a complex world, Cambridge University Press, https://doi.org/10.1017/9781108679053, 2019.
Callander, S.: Searching for good policies, Am. Polit. Sci. Rev., 105, 643–662, https://www.jstor.org/stable/23275345, 2011.
Calvin, K. V., Snyder, A., Zhao, X., and Wise, M.: Modeling land use and land cover change: using a hindcast to estimate economic parameters in gcamland v2.0, Geosci. Model Dev., 15, 429–447, https://doi.org/10.5194/gmd-15-429-2022, 2022.
Chen, M., Vernon, C. R., Huang, M., Calvin, K. V., and Kraucunas, I. P.: Calibration and analysis of the uncertainty in downscaling global land use and land cover projections from GCAM using Demeter (v1.0.0), Geosci. Model Dev., 12, 1753–1764, https://doi.org/10.5194/gmd-12-1753-2019, 2019.
Cosma, S., Rimo, G., and Cosma, S.: Conservation finance: What are we not doing? A review and research agenda, J. Environ. Manage., J. Environ. Manage., 336, 1–14, https://doi.org/10.1016/j.jenvman.2023.117649, 2023.
Dakin, R. and Ryder, T. B.: Reciprocity and behavioral heterogeneity govern the stability of social networks, P. Natl. Acad. Sci., 117, 2993–2999, https://doi.org/10.1073/pnas.1913284117, 2020.
Daugbjerg, C. and Feindt, P. H.: Post-exceptionalism in public policy: transforming food and agricultural policy, J. Eur. Public Pol., 24, 1565–1584, https://doi.org/10.1080/13501763.2017.1334081, 2017.
Davidson, M. R., Filatova, T., Peng, W., Verbeek, L., and Kucuksayacigil, F.: Simulating institutional heterogeneity in sustainability science, P. Natl. Acad. Sci., 121, e2215674121, https://doi.org/10.1073/pnas.2215674121, 2024.
Díez-Echavarría, L., Villegas-Palacio, C., Arango-Aramburo, S., and Ezzine-de-Blas, D.: Decoupling in governance: the land governance network in a region of the Colombian Andes, Land Use Policy, 133, 106880, https://doi.org/10.1016/j.landusepol.2023.106880, 2023.
Djekic, I.: Environmental Impact of Meat Industry – Current Status and Future Perspectives, Procedia Food Sci., 5, 61–64, https://doi.org/10.1016/j.profoo.2015.09.025, 2015.
Duffy, C., Prudhomme, R., Duffy, B., Gibbons, J., O'Donoghue, C., Ryan, M., and Styles, D.: GOBLIN version 1.0: a land balance model to identify national agriculture and land use pathways to climate neutrality via backcasting, Geosci. Model Dev., 15, 2239–2264, https://doi.org/10.5194/gmd-15-2239-2022, 2022.
Ekholm, T., Freistetter, N.-C., Rautiainen, A., and Thölix, L.: CLASH – Climate-responsive Land Allocation model with carbon Storage and Harvests, Geosci. Model Dev., 17, 3041–3062, https://doi.org/10.5194/gmd-17-3041-2024, 2024.
Fan, W., Ding, Y., Ning, L., Wang, S., Li, H., Yin, D., Chua, T.-S., and Li, Q.: A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models, arXiv [preprint], https://doi.org/10.48550/arXiv.2405.06211, 2024.
Feindt, P. H.: Policy-Learning and Environmental Policy Integration in the Common Agricultural Policy, 1973–2003, Public Admin., 88, 296–314, https://doi.org/10.1111/j.1467-9299.2010.01833.x, 2010.
Fischer, M., Ingold, K., Sciarini, P., and Varone, F.: Dealing with bad guys: Actor- and process-level determinants of the “devil shift” in policy making, J. Public Policy, 36, 309–334, https://doi.org/10.1017/S0143814X15000021, 2016.
Fischer, P., Schulz-Hardt, S., and Frey, D.: Selective exposure and information quantity: how different information quantities moderate decision makers' preference for consistent and inconsistent information, J. Pers. Soc. Psychol., 94, 231, https://doi.org/10.1037/0022-3514.94.2.94.2.231, 2008.
Gallegos, I. O., Rossi, R. A., Barrow, J., Tanjim, M. M., Kim, S., Dernoncourt, F., Yu, T., Zhang, R., and Ahmed, N. K.: Bias and fairness in large language models: A survey, Comput. Linguist., 50, 1097–1179, 2024.
Gigerenzer, G. and Goldstein, D. G.: Reasoning the fast and frugal way: models of bounded rationality, Psychol. Rev., 103, 650–669, https://doi.org/10.1037/0033-295X.103.4.650, 1996.
González, V. B.: Modelling adaptation strategies for Swedish forestry under climate and global change, University of Edinburgh, http://hdl.handle.net/1842/25380 (last access: 7 June 2024), 2016.
Groq: Groq – AI Acceleration Platform, https://groq.com/, last access: 22 August 2024.
Guo, J., Li, F. Y., Tuvshintogtokh, I., Niu, J., Li, H., Shen, B., and Wang, Y.: Past dynamics and future prediction of the impacts of land use cover change and climate change on landscape ecological risk across the Mongolian plateau, J. Environ. Manage., 355, 120365, https://doi.org/10.1016/j.jenvman.2024.120365, 2024.
Hallerberg, M. and Von Hagen, J.: Electoral institutions, cabinet negotiations, and budget deficits in the European Union, National Bureau of Economic Research, Cambridge, Mass., USA, https://doi.org/10.3386/w6341, 1997.
He, J., Rungta, M., Koleczek, D., Sekhon, A., Wang, F. X., and Hasan, S.: Does Prompt Formatting Have Any Impact on LLM Performance?, arXiv [preprint], https://doi.org/10.48550/arXiv.2411.10541, 2024.
Henle, K., Alard, D., Clitherow, J.,Cobb, P., Firbank,L., Kull, T., McCracken, D., Moritz, R., Niemelä, J., Rebane, M., Wascher, D., Watt, A., and Young, J.: Identifying and managing the conflicts between agriculture and biodiversity conservation in Europe – A review, Agr. Ecosyst. Environ., 124, 60–71, https://doi.org/10.1016/j.agee.2007.09.005, 2008.
Holzhauer, S., Brown, C., and Rounsevell, M.: Modelling dynamic effects of multi-scale institutions on land use change, Reg. Environ. Change, 19, 733–746, https://doi.org/10.1007/s10113-018-1424-5, 2019.
Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S. K. S., Lin, Z., Zhou, L., Ran, C., Xiao, L., Wu, C., and Schmidhuber, J.: MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework, arXiv [preprint], https://doi.org/10.48550/arXiv.2308.00352,2023.
IEC 61131-7: IEC 61131-7, https://plcopen.org/iec-61131-7, last access: 22 August 2024.
Ji, Z., Yu, T., Xu, Y., Lee, N., Ishii, E., and Fung, P.: Towards mitigating LLM hallucination via self reflection, in: Findings of the Association for Computational Linguistics: EMNLP 2023, https://doi.org/10.18653/v1/2023.findings-emnlp.123, 1827–1843, 2023.
Jones, B. D.: Bounded Rationality and Political Science: Lessons from Public Administration and Public Policy, J. Publ. Adm. Res. Theory, 13, 395–412, https://doi.org/10.1093/jpart/mug028, 2003.
Kimmich, C., Ehlers, M.-H., Kellner, E., Oberlack, C., Thiel, A., and Villamayor-Tomas, S.: Networks of action situations in social–ecological systems: current approaches and potential futures, Sustain. Sci., 18, 1–10, https://doi.org/10.1007/s11625-022-01278-w, 2023.
LangChain: LangChain, https://python.langchain.com/v0.1/docs/get_started/introduction/, last access: 9 May 2024.
LangGraph: LangGraph Introduction, https://www.langchain.com/langgraph, last access: 8 August 2025.
Lawrence, A., Houghton, J., Thomas, J., and Weldon, P.: Where Is the Evidence? Realising the Value of Grey Literature for Public Policy and Practice, Discuss. Pap., University of Nebraska-Lincoln, https://digitalcommons.unl.edu/scholcom (last access: 6 May 2024), 2014.
Lee, J., Kim, S., and Lee, J.: Public vs. Public: Balancing the Competing Public Values of Participatory Budgeting, Public Adm. Q., 46, 39–66, https://doi.org/10.37808/paq.46.1.3, 2022.
Levy, M., Alon, J., and Yoav, G.: Same task, more tokens: the impact of input length on the reasoning performance of large language models, arXiv [preprint], https://doi.org/10.48550/arXiv.2402.14848, 2024.
Llama: Meta-Llama-3-70B, https://www.llama.com/, last access: 22 August 2024.
Li, X., Wang, S., Zeng, S., Wu, Y., and Yang, Y.: A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges, Vicinagearth, 1, 9, https://doi.org/10.1007/s44336-024-00009-2, 2024.
Li, Y., Krishnamurthy, R., Raghavan, S., Vaithyanathan, S., and Jagadish, H. V.: Regular expression learning for information extraction. In Proceedings of the 2008 conference on empirical methods in natural language processing, 21–30, https://doi.org/10.5555/1613715.1613719, 2008.
Lindblom, C. E.: The science of muddling through, Read. Manag. Psychol., 4, 117–131, https://doi.org/10.2307/973677, 1989.
Liu, Z.: Cultural Bias in Large Language Models: A Comprehensive Analysis and Mitigation Strategies, J. Transcult. Commun., 3, 224–244, https://doi.org/10.1515/jtc-2023-0019, 2024.
Liu, Z., Yao, W., Zhang, J., Yang, L., Liu, Z., Tan, J., Choubey, P. K., Lan, T., Wu, J., Wang, H., Heinecke, S., Xiong, C., and Savarese, S.: AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System, arXiv [preprint], https://doi.org/10.48550/arXiv.2402.15538, 2024.
Machovina, B., Feeley, K. J., and Ripple, W. J.: Biodiversity conservation: The key is reducing meat consumption, Sci. Total Environ., 536, 419–431, https://doi.org/10.1016/j.scitotenv.2015.07.022, 2015.
Maes, J., Paracchini, M., Zulian, G., Dunbar, M., and Alkemade, R.: Synergies and trade-offs between ecosystem service supply, biodiversity, and habitat conservation status in Europe, Biol. Conserv., 155, 1–12, https://doi.org/10.1016/j.biocon.2012.06.016, 2012.
Mattison, E. H. and Norris, K.: Bridging the gaps between agricultural policy, land-use and biodiversity, Trends Ecol. Evol., 20, 610–616, https://doi.org/10.1016/j.tree.2005.08.011, 2005.
McGinnis, M. D.: Networks of Adjacent Action Situations in Polycentric Governance, Policy Stud. J., 39, 51–78, https://doi.org/10.1111/j.1541-0072.2010.00396.x, 2011.
Minaee, S., Mikolov, T., Nikzad, N., Chenaghlu, M., Socher, R., Amatriain, X., and Gao, J.: Large Language Models: A Survey, arXiv [preprint], https://doi.org/10.48550/arXiv.2402.06196, 2024.
Mizrahi, M., Kaplan, G., Malkin, D., Dror, R., Shahaf, D., and Stanovsky, G.: State of what art? A call for multi-prompt LLM evaluation, Trans. Assoc. Comput. Linguist., 12, 933–949, 2024.
Modarressi, A., Imani, A., Fayyaz, M., and Schütze, H.: Ret-llm: Towards a general read-write memory for large language models, arXiv [preprint], https://doi.org/10.48550/arXiv.2305.14322, 2023.
Murray-Rust, D., Brown, C., van Vliet, J., Alam, S. J., Robinson, D. T., Verburg, P. H., and Rounsevell, M.: Combining agent functional types, capitals and services to model land use dynamics, Environ. Modell. Softw., 59, 187–201, https://doi.org/10.1016/j.envsoft.2014.05.019, 2014.
Nair, S. and Howlett, M.: Policy myopia as a source of policy failure: adaptation and policy learning under deep uncertainty, Policy Polit., 45, 103–118, https://doi.org/10.1332/030557316X14788776017743, 2017.
Neri, S. and Ropele, T.: Imperfect information, real-time data and monetary policy in the euro area, Econ. J., 122, 651–674, https://doi.org/10.1111/j.1468-0297.2011.02488.x, 2012.
OpenAI: GPT-4o Documentation, https://platform.openai.com/docs/models, last access: 22 August 2024.
Park, J. S., O'Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., and Bernstein, M. S.: Generative Agents: Interactive Simulacra of Human Behavior, arXiv [preprint], https://doi.org/10.48550/arXiv.2304.03442, 2023.
Paz, D. B., Henderson, K., and Loreau, M.: Agricultural land use and the sustainability of social-ecological systems, Ecol. Model., 437, 109312, https://doi.org/10.1016/j.ecolmodel.2020.109312, 2020.
Perkins, O., Kasoar, M., Voulgarakis, A., Smith, C., Mistry, J., and Millington, J. D. A.: A global behavioural model of human fire use and management: WHAM! v1.0, Geosci. Model Dev., 17, 3993–4016, https://doi.org/10.5194/gmd-17-3993-2024, 2024.
Perković, G., Drobnjak, A., and Botički, I.: Hallucinations in LLMs: Understanding and Addressing Challenges, in: 2024 47th MIPRO ICT and Electronics Convention (MIPRO), 20–24 May 2024, Opatija, Croatia, https://doi.org/10.1109/MIPRO60963.2024.10569238, 2024.
Petrovic, Z., Djordjevic, V., Milicevic, D., Nastasijevic, I., and Parunovic, N.: Meat Production and Consumption: Environmental Consequences, Procedia Food Sci., 5, 235–238, https://doi.org/10.1016/j.profoo.2015.09.041, 2015.
Piantadosi, S. T.: Zipf's word frequency law in natural language: A critical review and future directions, Psychon. B. Rev., 21, 1112–1130, https://doi.org/10.3758/s13423-014-0585-6, 2014.
Qi, X., Wang, R. Y., Li, J., Zhang, T., Liu, L., and He, Y.: Ensuring food security with lower environmental costs under intensive agricultural land use patterns: A case study from China, J. Environ. Manage., 213, 329–340, https://doi.org/10.1016/j.jenvman.2018.02.048, 2018.
Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., Xu, J., Li, D., Liu, Z., and Sun, M.: ChatDev: Communicative Agents for Software Development, arXiv preprint, https://doi.org/10.48550/arXiv.2307.07924, 2024.
Radford, A., Narasimhan, K., Salimans, T., and Sutskever, I.: Improving language understanding by generative pre-training, Open AI, https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf (last access: 4 July 2024), 2018.
Rich, R. F.: Selective utilization of social science related information by federal policy-makers, Inquiry, 12, 239–245, 1975.
Simon, H. A.: Theories of bounded rationality, Decis. Organ., 1, 161–176, 1972.
Simon, H. A.: Administrative behavior, Simon and Schuster, ISBN 9780684835822, 2013.
Sinden, A.: In Defense of Absolutes: Combating the Politics of Power in Enviornmental Law, Iowa Law Rev., 90, 1405, https://ssrn.com/abstract=691344, 2004.
Sumers, T. R., Yao, S., Narasimhan, K., and Griffiths, T. L.: Cognitive Architectures for Language Agents, arXiv preprint, https://doi.org/10.48550/arXiv.2309.02427, 2024.
Tan, R., Xiong, C., and Kimmich, C.: An agent-situation-based model for networked action situations: Cap-and-trade land policies in China, Land Use Policy, 131, 106743, https://doi.org/10.1016/j.landusepol.2023.106743, 2023.
Tao, Y., Viberg, O., Baker, R. S., and Kizilcec, R. F.: Cultural bias and cultural alignment of large language models, PNAS Nexus, 3, 346, https://doi.org/10.1093/pnasnexus/pgae346, 2024.
Taubenfeld, A., Dover, Y., Reichart, R., and Goldstein, A.: Systematic biases in LLM simulations of debates, arXiv [preprint], https://doi.org/10.48550/arXiv.2402.04049, 2024.
Tesfaye, M., Kimengsi, J. N., and Giessen, L.: A policy mix for achieving ambitious goals on forest landscape restoration: Analyzing coherence and consistency in Ethiopia forest-related policy, Land Use Policy, 144, 107214, https://doi.org/10.1016/j.landusepol.2024.107214, 2024.
Tonmoy, S. M. T. I., Zaman, S. M. M., Jain, V., Rani, A., Rawte, V., Chadha, A., and Das, A.: A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models, arXiv [preprint], https://doi.org/10.48550/arXiv.2401.01313, 2024.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I.: Attention is all you need, Adv. Neural Inf. Process. Syst., 30, https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf (last access: 12 August 2024), 2017.
Waldron, A., Mooers, A. O., Miller, D. C., Nibbelink, N., Redding, D., Kuhn, T. S., Roberts, J. T., and Gittleman, J. L.: Targeting global conservation funding to limit immediate biodiversity declines, P. Natl. Acad. Sci., 110, 12144–12148, https://doi.org/10.1073/pnas.1221370110, 2013.
Wang, J., Lin, Y., Glendinning, A., and Xu, Y.: Land-use changes and land policies evolution in China's urbanization processes, Land Use Policy, 75, 375–387, https://doi.org/10.1016/j.landusepol.2018.04.011, 2018.
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., Zhao, W. X., Wei, Z., and Wen, J.: A survey on large language model based autonomous agents, Front. Comput. Sci., 18, 186345, https://doi.org/10.1007/s11704-024-40231-1, 2024a.
Wang, Z. Z., Mao, J., Fried, D., and Neubig, G.: Agent workflow memory, arXiv [preprint], https://doi.org/10.48550/arXiv.2409.07429, 2024b.
Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., Liu, J., Awadallah, A. H., White, R. W., Burger, D., and Wang, C.: AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation, arXiv [preprint], https://doi.org/10.48550/arXiv.2308.08155, 2023.
Yami, M., van Asten, P., Hauser, M., Schut, M., and Pali, P.: Participation without negotiating: Influence of stakeholder power imbalances and engagement models on agricultural policy development in Uganda, Rural Sociol., 84, 390–415, https://doi.org/10.1111/ruso.12229, 2019.
Yang, H., Yue, S., and He, Y.: Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions, arXiv [preprint], https://doi.org/10.48550/arXiv.2306.02224, 2023.
Yao, J.-Y., Ning, K.-P., Liu, Z.-H., Ning, M.-N., and Yuan, L.: LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples, arXiv [preprint], https://doi.org/10.48550/arXiv.2310.01469, 2023.
Zeng, Y.: Data for running InsNet-CRAFTY v1.0 (1.0), Zenodo [data set], https://doi.org/10.5281/zenodo.13944650, 2024a.
Zeng, Y.: Code for running InsNet-CRAFTY v1.0 (1.0), Zenodo [code], https://doi.org/10.5281/zenodo.13356487, 2024b.
Zeng, Y. and Byari, M.: Interactive visualization of InsNet-CRAFTY v1.0 agent textual output, https://crafty-abm.github.io/Interactive-visualization-of-InsNet-CRAFTY-v1.0-agent-textual-output/, last access: 10 March 2025.
Zeng, Y., Raymond, J., Brown, C., and Rounsevell, M.: Exploring outcome-driven policymaking on protected areas with an endogenous institutional model, J. Clean. Prod., 501, 145262, https://doi.org/10.1016/j.jclepro.2025.145262, 2025a.
Zeng, Y., Raymond, J., Brown, C., Byari, M., and Rounsevell, M.: Simulating endogenous institutional behaviour and policy implementation pathways within the land system, Ecol. Model., 501, 111032, https://doi.org/10.1016/j.ecolmodel.2025.111032, 2025b.
Zeng, Y., Brown, C., Raymond, J., Byari, M., Hotz, R., and Rounsevell, M.: Exploring the opportunities and challenges of using large language models to represent institutional agency in land system modelling, Earth Syst. Dynam., 16, 423–449, https://doi.org/10.5194/esd-16-423-2025, 2025c.
Zhang, Z., Bo, X., Ma, C., Li, R., Chen, X., Dai, Q., Zhu, J., Dong, Z., and Wen, J.-R.: A survey on the memory mechanism of large language model based agents, arXiv [preprint], https://doi.org/10.48550/arXiv.2404.13501, 2024.
Zhong, W., Guo, L., Gao, Q., Ye, H., and Wang, Y.: Memorybank: Enhancing large language models with long-term memory, in: Proceedings of the AAAI Conference on Artificial Intelligence, 38, 19724–19731, https://doi.org/10.1609/aaai.v38i17.29946, 2024.
Zhou, H., Feng, Z., Zhu, Z., Qian, J., and Mao, K.: UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation, arXiv [preprint], https://doi.org/10.48550/arXiv.2405.20612, 2024.
Zhou, X., Li, G., and Liu, Z.: LLM as DBA, arXiv [preprint], https://doi.org/10.48550/arXiv.2308.05481, 2023.
Short summary
Understanding environmental policy interventions is challenging due to complex institutional actor interactions. Large language models (LLMs) offer new solutions by mimicking the actors. We present InsNet-CRAFTY v1.0, a multi-LLM-agent model coupled with a land system model, simulating competing policy priorities. The model shows how LLM agents can simulate decision-making in institutional networks, highlighting both their potential and limitations in advancing land system modelling.
Understanding environmental policy interventions is challenging due to complex institutional...