Agri-SCHOLAR: Simulation-Grounded In-Season Rolling Advisories for Agricultural Crops Using LLM-Bounded Optimization

Geetha Charan; Vedant Balasubramaniam; Manojkumar Patil; V. Priyanka; Kodur Sai Vinay Sathvik; Rohit P Suresh; Mohammad Sufyan Azam; Y. Narahari

cs.AIOct 22, 2026

Agri-SCHOLAR: Simulation-Grounded In-Season Rolling Advisories for Agricultural Crops Using LLM-Bounded Optimization

Authors: Geetha Charan, Vedant Balasubramaniam, Manojkumar Patil, V. Priyanka, Kodur Sai Vinay Sathvik, Rohit P Suresh, Mohammad Sufyan Azam, Y. Narahari

Organizations: Indian Institute of Science, Bengaluru, India · University of Michigan, Ann Arbor, USA

Abstract

Existing agricultural advisories to farmers suffer from several limitations: (a) remain largely expert-driven, (b) do not adequately account for in-season weather, and (c) do not scale to individual farms. In this paper, our objective is to close these gaps by developing Agri-SCHOLAR (Simulation-Grounded Crop Harvest Optimization with LLM-Guided In-Season Advisory Rollouts). Agri-SCHOLAR is a rolling, in-season advisory framework that issues, at intervals of every few days or every week, a personalized advisory using the following information: soil and crop properties, observed weather to date, short-range forecast of weather, and a season extrapolation of weather based on historical analogs. The novelty and depth of Agri-SCHOLAR lies in each advisory being produced by a closed-loop system which couples multiple LLM agents with a powerful crop simulator (such as APSIM in our case). The simulator crucially serves as an evaluation oracle. In Agri-SCHOLAR, the LLM agents propose agronomically sound and feasible bounds on actionable parameters and an optimizer searches within those bounds against a multi-objective reward spanning yield, resource utilization, and economic feasibility. We conduct a detailed 11-year analysis of the maize crop in two selected locations of South Asia and show that Agri-SCHOLAR consistently outperforms the region's standard packages of practice and satisfactorily addresses the limitations of existing agricultural advisories.

Figures & tables

Symbol	Meaning	Source
$Y$	Grain yield	APSIM: [Maize].Grain.Wt
$SW_{t}$ , $DUL_{t}$ , $SAT_{t}$	Soil water, drained upper limit, and saturation of the profile on day $t$	APSIM: [Soil].Physical.[SWmm/DULmm/SATmm]
$N_{\text{demand}}$	Crop nitrogen demand, summed over leaf, stem, root, and grain organs	APSIM: sum of NDemand.Total over the organs
$D_{\text{cml}}$	Cumulative deep drainage	APSIM: [WaterBalance].Drainage
$L_{NO_{3}}$ , $L_{NH_{4}}$	Cumulative nitrate and ammonium leaching	APSIM: [WaterBalance].[LeachNO3/LeachNH4]
$SOC_{0}$ , $SOC_{H}$	Soil organic carbon (SOC) at the start and end of the horizon	APSIM: [Soil].Organic.Carbon

Table 1: Quantities used in the reward and their sources.

Panel of Figure 2 — Figure 2: Grain yield per season under PoP baseline and Agri-SCHOLAR.

Figure 3: Net profit per season under PoP baseline and Agri-SCHOLAR (irrigated region).

Region	Method	Yield(kg/ha)	Profit($/ha)	Prod. cost	Sust. penalty
Irrigated	PoP	6,477.55	5,959.33	284.02	495.33
	Agri-SCHOLAR	7,461.00	7,025.09	469.68	267.05
Rainfed	PoP	5,909.36	5715.15	149.63	282.81
	Agri-SCHOLAR	7,234.55	7,037.19	214.09	274.95

Table 2: Mean yield, net profit, production cost, and sustainability penalty over 11 seasons. Monetary values are in PPP-adjusted $/ha. Best value per column and region in bold (highest for yield and profit, lowest for cost and penalty).

Panel of Figure 4 — Figure 4: Drainage and Leaching per season (irrigated region).

Figure 6: Case study for irrigated region, 2023 season. (a) UreaN applied per week (b) Irrigation per week (c) Projected Yield

Variant	Yield (kg/ha)	Profit ($/ha)	Prod. cost	Sust. penalty
Agri-SCHOLAR	7,461.00	7,025.09	469.68	267.05
Loose bounds	7,614.82	7,199.86	401.24	320.73
	$\pm$ 1,785.82	$\pm$ 1,823.07	$\pm$ 61.40	$\pm$ 107.33
No bounds	7,082.64	1,682.69	4,451.40	1,234.11
	$\pm$ 2,153.72	$\pm$ 3,117.25	$\pm$ 2,521.46	$\pm$ 1,503.77

Table 3: ABA ablation: irrigated region, mean over 11 seasons.

Parameter	Notation	LCU	$	Source/Basis
Grain price (per kg)	$p_{g}$	20.90	1.04	Support price [ 28 ]
UreaN (per kg N)	$p_{1}^{F}$	13.04	0.65	Retail price [ 29 ]
DAP (per kg)	$p_{2}^{F}$	27.00	1.34	Retail price [ 29 ]
Mulch (per kg)	$p_{M}$	2.00	0.10	Residue and fodder prices [ 30 ]
Water (per mm)	$p_{w}$	2.50	0.12	Irrigation charges [ 31 , 32 ]
Labour (per operation)	$p_{L}$	350.00	17.42	Rural wage [ 33 ]

Table 4: Cost and penalty parameters used in Optimization Agent (OA).

Table 10

Table 11

AI-Assisted Decision Making

AI-assisted decision making studies how computational systems can inform human choices while accounting for context, uncertainty, and consequences.

See all 144 papers

Agri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generation
Jul 1, 2026Vedant Balasubramaniam, Geetha Charan, Manojkumar Patil +4Multi-Agent LLM Systems AI-Assisted Decision Making
Indian Institute of Science, Bengaluru · BNM Institute of Technology, Bengaluru
AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents
Feb 17, 2026Zhixing Zhang, Jesen Zhang, Hao Liu +4Tool-Augmented Language Model Agents LLM Agents
Sun Yat-sen University
Fine-Tuning General-Purpose Large Language Models for Agricultural Applications:A Reproducible Framework and Evaluation Protocol Based on Qwen3-8B
Jun 27, 2026Zhaoyang Li, Ruijie Zhang, Jiaqi Liu +1LLM Fine-Tuning
1Sanya University · 2Hebei International Studies University

Jul 1, 2026J/K move · Enter open · S save

Agri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generation

Vedant Balasubramaniam, Geetha Charan, Manojkumar Patil, Rohit P Suresh+3

Indian Institute of Science, Bengaluru · BNM Institute of Technology, Bengaluru

Multi-Agent LLM Systems AI-Assisted Decision Making Agentic Reasoning

Open paper AskPDF arXiv

Agricultural advisory systems face a fundamental tension: static agronomic guidelines offer consistent, evidence-based 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 APSIM-based 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.

Abstract

AI-Assisted Decision Making

Explore similar work

Agri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generation

AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents

Fine-Tuning General-Purpose Large Language Models for Agricultural Applications:A Reproducible Framework and Evaluation Protocol Based on Qwen3-8B