[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81770-en":3,"doc-seo-81770-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":20,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},81770,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Agri-SAGE Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generation","Agricultural advisory systems face a core mismatch between static agronomic guidelines and real in-season variability. LLM-powered advisors may produce recommendations that are linguistically credible yet physiologically unconvincing. Agri-SAGE introduces a closed-loop framework combining retrieval-grounded multi-agent LLM reasoning with APSIM-based biophysical simulation to generate and validate advisories. A 10-year retrospective compares Plan-and-Solve, Tree of Thoughts, and Reflexion against static PoP baselines, achieving stronger agronomic outcomes while reducing compute via episodic memory.","Agri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generation  \nVedant Balasubramaniam 1 , Geetha Charan 1 , Manojkumar Patil 1 , Rohit P Suresh 1 , V Priyanka 1 ,  \nKodur Sai Vinay Sathvik2 and Y. Narahari 1  \narXiv :2607 .00454v 1 [ cs .AI] 1 Jul 2026  \nAbstract—Agricultural advisory systems face a fundamental tension: static agronomic guidelines offer consistent, evidencebased recommendations, yet remain blind to in-season variability and dynamic uncertainties. Recent advisory systems powered by LLMs are liable for a different risk of generating recommendations that are agronomically credible but physiologically unconvincing. Agri-SAGE is a closed-loop framework designed to resolve the above two limitations by integrating retrieval-grounded multi-agent LLM reasoning with APSIMbased biophysical simulation, to generate and validate agronomic advisories.. To assess this framework, we evaluate three reasoning approaches, namely Plan-and-Solve, Tree of Thoughts, and Reflexion, over a 10-year retrospective analysis. All three significantly outperform static PoP (Package-of-Practice) baselines, with Tree of Thoughts achieving impressive peak yields. At the same time, Reflexion achieves comparable agronomic outcomes at substantially lower computational cost by leveraging cross-seasonal episodic memory.  \nI. INTRODUCTION  \nAgriculture remains the cornerstone of food security and rural livelihoods across much of the developing world. In India, where a substantial share of the population depends on farming for subsistence and income, the quality of agricultural guidance available to farmers has profound implications for productivity and economic stability.  \nTraditionally, agricultural advisories in India are delivered through Packages of Practices (PoPs) . which contain agronomic guidelines derived from extensive field trials and agronomic research. These recommendations typically include land preparation methods, fertilizer schedules, irrigation practices, and pest management strategies.  \nWhile scientifically grounded, PoPs are inherently static as they are issued before the cropping season at the agroclimatic zone level and updated infrequently. As a result, they cannot adapt to season variability such as weather shocks, pest outbreaks, or localized soil heterogeneity. Consequently, farmers receive recommendations that may not be suitable to their specific field conditions.  \nTo partially address this limitation, agricultural advisory systems also provide In-Season Advisories. These are dynamic, time-sensitive recommendations generated during the cropping season based on real-time environmental signals, including weather forecasts, temperature patterns, pest  \n1Indian Institute of Science, Bengaluru {vedantb, geethacharan, pmanojkumar, rohitpsuresh, priyankav, [narahari](narahari}@iisc.ac.in)[}](narahari}@iisc.ac.in)[@iisc.ac.in](narahari}@iisc.ac.in)  \n2BNM Institute of Technology, Bengaluru [sathvik2004@gmail.com](sathvik2004@gmail.com)  \nincidence, and crop phenological stages. In India, AgroMeteorological Field Units (AMFUs) are responsible for generating such advisories. However, these advisories remain largely manual and expert-driven, limiting scalability and the ability to personalize recommendations.  \nRecent advances in LLMs have enabled agricultural advisory systems capable of synthesizing large agronomic knowledge bases and interacting with farmers through natural language interfaces. While these systems significantly improve accessibility and knowledge dissemination, they remain constrained as they may generate plausible but incorrect recommendations.  \nTo address these limitations, we introduce Agri-SAGE, a novel framework that reconceives the traditional Package of Practices as a dynamic, context-aware agronomic plan. At its core, Agri-SAGE uses a multi-agent LLM architecture, with specialized agents to generate, evaluate, and refine agricultural recommendations. By combining agro","cbCaimb7aNNnWiGW","https://ap.wps.com/l/cbCaimb7aNNnWiGW","pdf",496864,6,1,"English","en",105,"# Introduction\n## Contributions\n# Related Work\n## LLM-Based Agricultural Advisory Systems","[{\"question\":\"What limitations does Agri-SAGE aim to address in agricultural advisory generation?\",\"answer\":\"Agri-SAGE targets the gap between static Package of Practices and dynamic in-season uncertainties, and it reduces the risk of LLM recommendations that are agronomically fluent but physiologically unconvincing.\"},{\"question\":\"How does Agri-SAGE ensure recommendations are biophysically feasible?\",\"answer\":\"It validates generated advisory plans using APSIM, a crop process-based simulation model, grounding textual recommendations in crop physiology.\"},{\"question\":\"Which reasoning approaches are evaluated, and how do they compare in outcomes and cost?\",\"answer\":\"The document evaluates Plan-and-Solve, Tree of Thoughts, and Reflexion over a 10-year retrospective. Tree of Thoughts delivers the best peak yields, while Reflexion achieves comparable agronomic results with substantially lower computational cost through cross-seasonal episodic memory.\"}]",1784176035,15,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"agri-sage-simulation-grounded-multi-agent-llm-for-context-aware-agricultural-advisory-generation","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/agri-sage-simulation-grounded-multi-agent-llm-for-context-aware-agricultural-advisory-generation/81770/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What limitations does Agri-SAGE aim to address in agricultural advisory generation?","Question",{"text":75,"@type":76},"Agri-SAGE targets the gap between static Package of Practices and dynamic in-season uncertainties, and it reduces the risk of LLM recommendations that are agronomically fluent but physiologically unconvincing.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Agri-SAGE ensure recommendations are biophysically feasible?",{"text":80,"@type":76},"It validates generated advisory plans using APSIM, a crop process-based simulation model, grounding textual recommendations in crop physiology.",{"name":82,"@type":73,"acceptedAnswer":83},"Which reasoning approaches are evaluated, and how do they compare in outcomes and cost?",{"text":84,"@type":76},"The document evaluates Plan-and-Solve, Tree of Thoughts, and Reflexion over a 10-year retrospective. Tree of Thoughts delivers the best peak yields, while Reflexion achieves comparable agronomic results with substantially lower computational cost through cross-seasonal episodic memory.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]