Agri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generation
Quick Answer
This paper shows that Agri-SAGE integrates retrieval-grounded multi-agent LLM reasoning with APSIM-based simulations to enhance agricultural advisory systems, outperforming static guidelines.
Quick Take
Evaluated over a decade, it shows Tree of Thoughts achieving peak yields while Reflexion offers similar outcomes at lower computational costs through episodic memory.
Key Points
- Agri-SAGE addresses limitations of static agronomic guidelines and -generated recommendations.
- Three reasoning approaches evaluated: Plan-and-Solve, Tree of Thoughts, and Reflexion.
- Tree of Thoughts achieved impressive peak yields in the 10-year analysis.
- Reflexion provided comparable agronomic outcomes at significantly lower computational costs.
- The framework enhances context-aware agricultural advisories for better decision-making.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2607.00454 [cs.AI] |
| (or arXiv:2607.00454v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.00454 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Geetha Charan [view email]
[v1]
Wed, 1 Jul 2026 05:18:20 UTC (583 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.