用模拟验证大模型农业建议，兼顾科学性和实时性。
Agri-SAGE: Simulation-Grounded Multi-Agent LLM for Context-Aware Agricultural Advisory Generation
- 融合模拟与多智能体大模型，闭环生成建议。
- 树状思维法实现最高产量，优于传统方案。
- 反思机制节省计算成本，适合实际部署。
农业咨询系统面临根本矛盾：静态农艺指南虽具证据支持，却无法应对生长期变化与动态不确定性。近期基于大模型的咨询系统则存在推荐看似合理但生理上不合理的问题。Agri-SAGE 是一个闭环框架，将检索增强的多智能体大模型推理与 APSIM 生物物理模拟相结合，用于生成并验证农艺建议。为评估该框架，我们在十年回溯分析中对比三种推理方法：计划-求解、思维树（Tree of Thoughts）和反思（Reflexion）。三者均显著优于静态的 PoP（实践包）基线，其中思维树实现最高产量；而反思方法在计算成本大幅降低的前提下，达到相近农艺效果，得益于跨季情景记忆机制。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。