Skip to content
References

The literature behind Croptimum.

Research papers that inform Croptimum's architecture and approach, grouped by topic.

Coming soon

Single Agent Systems

Foundational work on single-agent approaches and where they fit in agricultural decision support.

Papers being curated — check back soon.

1 paper

Limitations with Single Agent

Why single-agent architectures fall short for cross-domain, real-world agricultural reasoning.

Accelerating Earth Science Discovery via Multi-Agent LLM Systems

2025

D. Pantiukhin, B. Shapkin, I. Kuznetsov, A. A. Jost, N. Koldunov · Frontiers in AI · arXiv 2503.05854

Summary

A perspective on Multi-Agent Systems powered by LLMs for the geosciences. Presents PANGAEA GPT, a specialised MAS pipeline integrated with the PANGAEA Earth-and-Environmental-Science database, demonstrating how MAS-driven workflows manage complex, multi-format scientific data.

“while single-agent approaches can handle specific, well-defined tasks, they often struggle with interdisciplinary queries that require specialized knowledge across diverse data formats and domains.”
Relevance to Croptimum

Cited to justify the multi-agent architecture. Agricultural decision support spans crops, soil, weather, and pests — exactly the kind of cross-domain workload single-agent setups handle poorly.

View paper
4 papers

Multi Agent Systems

Recent multi-agent frameworks applied to agricultural decision support and farmer advisory.

AgroAskAI: A Multi-Agentic AI Framework for Supporting Smallholder Farmers' Enquiries Globally

2025

N. A. Cantonjos, A. Biswas · arXiv 2512.14910

Summary

A modular, role-specialised multi-agent framework for smallholder farmers. Uses a chain-of-responsibility pattern to coordinate autonomous agents with real-time tools (weather, geospatial data) and a dedicated critique agent for hallucination control. Supports multilingual interaction.

Relevance to Croptimum

Closest peer to Croptimum's architecture. Informs the orchestrator + specialised-agent + judge pattern that Croptimum uses.

View paper

Agentic AI-driven autonomous decision support system for smart agriculture

2026

Scientific Reports

Summary

Soil2Harvest-AI — an agentic framework for end-to-end crop yield optimisation. Combines soil image classification (Custom CNN, 92.88% accuracy), regression-based soil parameter estimation, real-time weather integration, and explainable-AI overlays (SHAP, LIME).

Relevance to Croptimum

Validates the model of orchestrating multiple agricultural ML sub-tasks behind a single user-facing decision support interface.

View paper

An Agent-Based Model-Driven Decision Support System for Assessment of Agricultural Vulnerability of Sugarcane Facing Climatic Change

2021

A. E. Badillo-Márquez et al. · Mathematics (MDPI) 9(23) 3061

Summary

An agent-based model combining fuzzy logic and system dynamics to evaluate sugarcane vulnerability to climate change. Uses a three-stage methodology: vulnerability indicators, crop vulnerability, and total system vulnerability.

Relevance to Croptimum

Demonstrates how agent-based decision support translates climate variables into actionable crop-vulnerability assessments — directly applicable to Croptimum's climate-coupled reasoning.

View paper

MASSAI: Multi-agent system for simulating sustainable agricultural intensification of smallholder farms in Africa

2023

Heliyon · ScienceDirect

Summary

A multi-agent system that operationalises the Sustainable Agricultural Intensification framework. Pairs an Environmental Module (nutrient inputs and outputs) with a Behavioural Module (farmer decisions on fertilizer, manure, biological N fixation) to simulate sustainability trajectories on managed plots.

Relevance to Croptimum

Reference for separating environmental modelling from behavioural decision-making — informs Croptimum's split between Weather/Soil agents and the orchestrator/advisory layer.

View paper
2 papers

RAG

Retrieval-Augmented Generation approaches that ground LLM responses in verified agricultural knowledge.

Empowering farmers with artificial intelligence: a retrieval-augmented generation based large language model advisory framework

2026

Journal of Agricultural Engineering

Summary

A RAG-based agricultural advisory system covering crop cultivation, pest and disease management, and fertilizer application across five crops (maize, ragi, sweet potato, cotton, groundnut). Processes Package of Practices documents via semantic chunking and benchmarks four LLMs.

Relevance to Croptimum

Concrete evidence that RAG on government and extension-service documents produces deployable farmer advisory — supports Croptimum's choice to ground responses in verified agronomic corpora.

View paper

AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval

2026

S. Banerji Seal et al. · arXiv 2604.16353

Summary

A configurable RAG framework that decomposes information access into declarative stages (query refinement, sub-query planning, retrieval, synthesis, evaluation). Integrates 1B-parameter LLMs with adaptive retrievers and enforces deterministic citation (59–73% perfect citation accuracy) to eliminate citation hallucination.

Relevance to Croptimum

Architectural reference for Croptimum's Agentic RAG layer — particularly the deterministic citation mechanism, which aligns with the Judge Agent and the project's 'no fabricated claims' stance.

View paper