多智能体大模型在农业中的应用研究与展望

doi:10.12133/j.smartag.SA202503026

Smart Agriculture ›› 2025, Vol. 7 ›› Issue (5): 37-51.doi: 10.12133/j.smartag.SA202503026

• 专刊--光智农业创新技术与应用 • 上一篇下一篇

多智能体大模型在农业中的应用研究与展望

赵莹萍¹, 梁锦名¹, 陈贝章¹, 邓小玲⁴^,⁵, 张奕⁴^,⁵, 熊征¹^,²^,³, 潘明¹^,²^,³, 孟祥宝¹^,²^,³()

^1. 深圳市现代农业装备研究院，广东深圳 518001，中国
^2. 广东省现代农业装备研究院，广东广州 510630，中国
^3. 农业农村部华南现代农业智能装备重点实验室，广东广州 510630，中国
^4. 华南农业大学电子工程学院（人工智能学院），广东广州 510642，中国
^5. 国家精准农业航空施药技术国际联合研究中心，广东广州 510642，中国

收稿日期:2025-03-25 出版日期:2025-09-30
基金项目:
广东省科学技术厅项目(2023B0202090001); 广东省农业农村厅项目(2024CXTD18)
作者简介:
赵莹萍，博士研究生，研究方向为计算机视觉算法在农业中的应用、智慧交通等。E-mail： yingping.zhao@gmail.com
通信作者:
孟祥宝，硕士，教授级高级工程师，研究方向为智慧农业，智能农机等。E-mail： mengxiangbao@126.com

Applications Research Progress and Prospects of Multi-Agent Large Language Models in Agricultural

ZHAO Yingping¹, LIANG Jinming¹, CHEN Beizhang¹, DENG Xiaoling⁴^,⁵, ZHANG Yi⁴^,⁵, XIONG Zheng¹^,²^,³, PAN Ming¹^,²^,³, MENG Xiangbao¹^,²^,³()

^1. Shenzhen Modern Agricultural Equipment Research Institute, Shenzhen 518001, China
^2. Guangdong Modern Agricultural Equipment Research Institute, Guangzhou 510630, China
^3. Key Laboratory of Modern Agricultural Intelligent Equipment in South China, Ministry of Agriculture and Rural Affairs, Guangzhou 510630, China
^4. College of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, China
^5. National Center for International Collaboration Research on Precision Agricultural Aviation Pesticides Spraying Technology, Guangzhou 510642, China

Received:2025-03-25 Online:2025-09-30
Foundation items:Project of the Department of Science and Technology of Guangdong Province(2023B0202090001); Project of the Department of Agriculture and Rural Affairs of Guangdong Province(2024CXTD18)
About author:
ZHAO Yingping, E-mail: yingping.zhao@gmail.com
Corresponding author:
MENG Xiangbao, E-mail: mengxiangbao@126.com

摘要/Abstract

摘要：

［目的/意义］ 随着多智能体系统和大模型技术的迅速发展，其在农业领域的应用将继续成为推动农业现代化和智能化的重要驱动力。本文旨在为农业数字化转型提供理论支持和实践参考，助力农业生产的精准化、智能化和可持续发展。 ［进展］ 本文首先阐述了多智能体系统和大语言模型的基本概念，系统梳理了多智能体系统和大语言模型的基本原理与框架。其次，着重分析了多智能体大模型的技术特点及其在农业中的潜在价值，列举了大模型在农业中的研究和应用状况，提出了大模型在农业中的应用架构和多智能体协作流程。最后，指出多智能体大模型在农业领域的核心挑战和未来研究方向。 ［结论/展望］ 多智能体大模型将凭借其高效协作与场景交互能力，有望在“耕、种、管、收”全流程智能化管理、农业灾害预警与应急决策、品种改良与育种创新等方面发挥更大作用。然而，当前多智能体大模型仍面临可解释性不足、幻觉问题，以及多模态数据的采集和处理方面的挑战。未来需通过引入更先进的推理机制、构建高效的知识库，以及开发针对农业场景的多模态大模型，进一步提升系统的可靠性和效率，为农业的智能化发展提供强有力的技术支持。

关键词: 多智能体, 大语言模型, 农业应用, 智能决策, 深度学习, 智慧农业

Abstract:

[Significance] With the rapid advancement of large language models (LLM) and multi-agent systems, their integration, multi-agent large language models, is emerging as a transformative force in modern agriculture. Agricultural production involves complex, sequential, and highly environment-dependent processes, including tillage, planting, management, and harvesting. Traditional intelligent systems often struggle with the diversity, uncertainty, and coordination of these stages' demand. Multi-agent LLMs offer a new paradigm for agricultural intelligence by combining deep semantic understanding with distributed collaboration and adaptive coordination. Through role specialization, real-time perception, and cooperative decision-making, they can decompose complex workflows, adapt to changing conditions, and enable robust, full-process automation, making them well-suited to the challenges of modern agriculture. More importantly, their application marks a critical step toward the digital transformation, precision management, and sustainable development of agriculture. By enabling intelligent decision-making across the entire agricultural lifecycle, they provide both theoretical foundations and practical tools for building next-generation smart and unmanned farming systems. [Progress] The core concepts of multi-agent LLMs are first elucidated, covering the composition and characteristics of multi-agent systems as well as the development and training pipelines of LLMs. Then, the overall architecture of multi-agent systems is presented, encompassing both the environments in which agents operate and their internal structures. The collaborative patterns of multi-agent LLMs are then examined in terms of coordination structures and temporal organization. Following this, interaction mechanisms are discussed from multiple dimensions, including interactions between agents and the external environment, inter-agent communication, communication protocol frameworks, and communication security. To demonstrate the varying task specializations of different multi-agent frameworks, a comparative benchmark survey table is provided by synthesizing benchmark tasks and results reported in existing studies. The results show that different multi-agent large language model architectures tend to perform better on specific types of tasks, reflecting the influence of agent framework design characteristics such as role assignment strategies, communication protocols, and decision-making mechanisms. Furthermore, several representative architectures of multi-agent LLMs, as proposed in existing studies, are briefly reviewed. Based on their design features, their potential applicability to agricultural scenarios is discussed. Finally, current research progress and practical applications of LLMs, multimodal large models, and multi-agent LLMs in the agricultural domain are surveyed. The application architecture of agricultural LLMs is summarized, using rice cultivation as a representative scenario to illustrate the collaborative process of a multi-agent system powered by LLMs. This process involves data acquisition agents, data processing agents, task allocation and coordination agents, task execution agents, and feedback and optimization agents. The roles and functions of each kind of agent in enabling automated and intelligent operations throughout the entire agricultural lifecycle, including tillage, planting, management, and harvesting, are comprehensively described. In addition, drawing on existing research on multimodal data processing, the pseudocode is provided to illustrate the basic logic of the data processing agents. [Conclusions and Prospects] Multi-agent LLMs technology holds vast promise in agriculture but still confronts several challenges. First, limited model interpretability, stemming from opaque internal reasoning and high-dimensional parameter mappings, hinders decision transparency, traceability, user trust, and debugging efficiency. Second, model hallucination is significant, probabilistic generation may deviate from facts, leading to erroneous environmental perception and decisions that cause resource waste or crop damage. Third, multi-modal agricultural data acquisition and processing remain complex due to non-uniform equipment standards, heterogeneous data, and insufficient cross-modal reasoning, complicating data fusion and decision-making. Future directions include: (1) enhancing interpretability via chain-of-thought techniques to improve reasoning transparency and traceability; (2) reducing hallucinations by integrating knowledge bases, retrieval-augmented generation, and verification mechanisms to bolster decision reliability; and (3) standardizing data formats to strengthen cross-modal fusion and reasoning. These measures will improve system stability and efficiency, providing solid support for the advancement of smart agriculture.

Key words: multi-agent, large language models, agricultural applications, intelligent decision-making, deep learning, smart agriculture

中图分类号:

TP18
S126

赵莹萍, 梁锦名, 陈贝章, 邓小玲, 张奕, 熊征, 潘明, 孟祥宝. 多智能体大模型在农业中的应用研究与展望[J]. 智慧农业(中英文), 2025, 7(5): 37-51.

ZHAO Yingping, LIANG Jinming, CHEN Beizhang, DENG Xiaoling, ZHANG Yi, XIONG Zheng, PAN Ming, MENG Xiangbao. Applications Research Progress and Prospects of Multi-Agent Large Language Models in Agricultural[J]. Smart Agriculture, 2025, 7(5): 37-51.

图/表 10

图1

图2

图3

图4

图5

表1

图6

图7

图8

表2

多模态数据融合伪代码

输入：

图像数据 $I$ （例如：遥感图像、作物生长图像）

传感器数据 $S$ （例如：温湿度、光照、土壤湿度）

文本数据 $T$ （例如：农业管理日志、天气报告）

步骤：

（1）数据预处理

对图像数据 $I$ 进行标准化、裁剪或增强等

对传感器数据 $S$ 进行去噪、插值、单位标准化

对文本数据 $T$ 进行分词、去停用词

（2）特征提取

使用图像模型（如ViT）提取图像特征：

$F i = I m a g e E n c o d e r (I)$

使用时间序列模型（如长短时记忆（Long Short Term Memory， LSTM））提取传感器数据特征：

$F s = S e n s o r E n c o d e r (S)$

使用文本模型（如BERT）提取文本特征：

$F t = T e x t E n c o d e r (T)$

（3）特征对齐

将不同模态的特征映射到相同的维度空间：

$F i' = A l i g n (F i)$

$F s' = A l i g n (F s)$

$F t' = A l i g n (F t)$

（4）特征融合

$F a l l = F u s i o n (F i', F s', F t')$

输出：

融合后的统一特征表示 $F a l l$ ，作为下游任务的输入基础

表2

参考文献 77

[1]	ANNEPAKA Y, PAKRAY P. Large language models: A survey of their development, capabilities, and applications[J]. Knowledge and information systems, 2025, 67(3): 2967-3022.
[2]	WANG Z C, CHU Z B, DOAN T V, et al. History, development, and principles of large language models: An introductory survey[J]. AI and ethics, 2025, 5(3): 1955-1971.
[3]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]// 31st Conference on Neural Information Processing System. Red Hook, New York, USA: Curran Associates Inc., 2017: 5998-6008.
[4]	DEVLIN J, CHANG M W, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[EB/OL]. arXiv:1810.04805v2, 2019.
[5]	RADFORD A, NARASIMHAN K, SALIMANS T, et al. Improving language understanding by generative pre-training[R]. OpenAI, 2018. [2025-04-30]. https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf.
[6]	RADFORD A, WU J, CHILD R, et al. Language models are unsupervised multitask learners[R]. OpenAI blog, 2019. [2025-04-30]. https://cdn.openai.com/better-language-models/language_mo dels_are_unsupervised_multitask_learners.pdf.
[7]	BROWN T, MANN B, RYDER N, et al. Language models are few-shot learners[EB/OL]. arXiv: 2005.14165, 2020.
[8]	CHOWDHERY A, NARANG S, DEVLIN J, et al. PaLM: Scaling language modeling with pathways[J]. Journal of machine learning research, 2023, 24(240): 1-113.
[9]	TEAM G, ANIL R, BORGEAUD S, et al. Gemini: A family of highly capable multimodal models[EB/OL]. arXiv: 2312.11805, 2023.
[10]	ACHIAM J, ADLER S, AGARWAL S, et al. GPT-4 technical report[EB/OL]. arXiv: 2303.08774, 2023.
[11]	YANG A, YANG B S, HUI B Y, et al. Qwen2 technical report[EB/OL]. arXiv: 2407.10671, 2024.
[12]	BAI S, CHEN K Q, LIU X J, et al. Qwen 2.5-VL technical report[EB/OL]. arXiv: 2502.13923, 2025.
[13]	TOUVRON H, MARTIN L, STONE K, et al. Llama 2: Open foundation and fine-tuned chat models[EB/OL]. arXiv: 2307.09288, 2023.
[14]	GRATTAFIORI A, DUBEY A, JAUHRI A, et al. The llama 3 herd of models[EB/OL]. arXiv: 2407.21783, 2024.
[15]	LIU A X, FENG B, XUE B, et al. DeepSeek-V3 technical report[EB/OL]. arXiv: 2412.19437, 2024.
[16]	GUO D Y, YANG D J, ZHANG H W, et al. DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning[EB/OL]. arXiv: 2501.12948, 2025.
[17]	TRAN K T, DAO D, NGUYEN M D, et al. Multi-agent collaboration mechanisms: A survey of LLMs[EB/OL]. arXiv: 2501.063 22, 2025.
[18]	DORRI A, KANHERE S S, JURDAK R. Multi-agent systems: A survey[J]. IEEE access, 2018, 6: 28573-28593.
[19]	GUO T C, CHEN X Y, WANG Y Q, et al. Large language model based multi-agents: A survey of progress and challenges[EB/OL]. arXiv: 2402.01680, 2024.
[20]	JULIAN V, BOTTI V. Multi-agent systems[J]. Applied sciences, 2019, 9(7): ID 1402.
[21]	ZHAO W X, ZHOU K, LI J Y, et al. A survey of large language models[EB/OL]. arXiv: 2303.18223, 2023.
[22]	KAPLAN J, MCCANDLISH S, HENIGHAN T, et al. Scaling laws for neural language models[EB/OL]. arXiv: 2001.08361, 2020.
[23]	LI P F, ZHANG M, LIN P J, et al. Conditional embedding pre-training language model for image captioning[J]. Neural processing letters, 2022, 54(6): 4987-5003.
[24]	DAN Y H, LEI Z K, GU Y Y, et al. EduChat: A large-scale language model-based chatbot system for intelligent education[EB/OL]. arXiv: 2308.02773, 2023.
[25]	KIANIAN R, SUN D Y, CROWELL E L, et al. The use of large language models to generate education materials about uveitis[J]. Ophthalmology retina, 2024, 8(2): 195-201.
[26]	KUNG T H, CHEATHAM M, MEDENILLA A, et al. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models[J]. PLoS digital health, 2023, 2(2): ID e0000198.
[27]	SALLAM M. ChatGPT utility in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns[J]. Healthcare, 2023, 11(6): ID 887.
[28]	SINGHAL K, TU T, GOTTWEIS J, et al. Toward expert-level medical question answering with large language models[J]. Nature medicine, 2025, 31(3): 943-950.
[29]	WU S J, IRSOY O, LU S, et al. Bloomberggpt: A large language model for finance[EB/OL]. arXiv: 2303.17564, 2023.
[30]	HUANG A H, WANG H, YANG Y. FinBERT: A large language model for extracting information from financial text[J]. Contemporary accounting research, 2023, 40(2): 806-841.
[31]	HUANG J M, XIAO M X, LI D, et al. Open-finllms: Open multimodal large language models for financial applications[EB/OL]. arXiv: 2408.11878, 2024.
[32]	PARK J S, O'BRIEN J, CAI C J, et al. Generative agents: Interactive simulacra of human behavior[C]// Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. New York, USA: ACM, 2023.
[33]	RASHEED Z, WASEEM M, AHMAD A, et al. Can large language models serve as data analysts? A multi-agent assisted approach for qualitative data analysis[EB/OL]. arXiv: 2402.01386, 2024.
[34]	FRAIWAN M, KHASAWNEH N. A review of ChatGPT applications in education, marketing, software engineering, and healthcare: Benefits, drawbacks, and research directions[EB/OL]. arXiv: 2305.00237, 2023.
[35]	TIRO D. The possibility of applying ChatGPT (AI) for calculations in mechanical engineering[M]// New Technologies, Development and Application VI. Cham: Springer Nature Switzerland, 2023: 313-320.
[36]	PAL S, BHATTACHARYA M, LEE S S, et al. A domain-specific next-generation large language model (LLM) or ChatGPT is required for biomedical engineering and research[J]. Annals of biomedical engineering, 2024, 52(3): 451-454.
[37]	AGASHE S, FAN Y, WANG X E. LLM-coordination: Evaluating and analyzing multi-agent coordination abilities in large language models[EB/OL]. arXiv: 2310.03903, 2023.
[38]	LI G H, HAMMOUD H, ITANI H, et al. Camel: Communicative agents for "mind" exploration of large language model society[EB/OL]. arXiv:2303.17760v2, 2023.
[39]	HONG S R, ZHUNG M C, CHEN J Q, et al. Metagpt: Meta programming for multi-agent collaborative framework[EB/OL]. arXiv: 2308.00352, 2023.
[40]	CHEN G Y, DONG S W, SHU Y, et al. Autoagents: A framework for automatic agent generation[EB/OL]. arXiv: 2309.17288, 2023.
[41]	QIAN C, XIE Z H, WANG Y F, et al. Scaling large-language-model-based multi-agent collaboration[EB/OL]. arXiv: 2406.07155, 2024.
[42]	ZHUGE M C, WANG W Y, KIRSCH L, et al. Language agents as optimizable graphs[EB/OL]. arXiv: 2402.16823, 2024.
[43]	CHEN W Z, SU Y S, ZUO J W, et al. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents[EB/OL]. arXiv: 2308.10848, 2023.
[44]	LIU Z W, YAO W R, ZHANG J G, et al. Agentlite: A lightweight library for building and advancing task-oriented LLM agent system[EB/OL]. arXiv: 2402.15538, 2024.
[45]	ZHANG B, MAO H Y, RUAN J Q, et al. Controlling large language model-based agents for large-scale decision-making: An actor-critic approach[EB/OL]. arXiv: 2311.13884, 2023.
[46]	SMITH. The contract net protocol: High-level communication and control in a distributed problem solver[J]. IEEE transactions on computers, 1980, C-29(12): 1104-1113.
[47]	PAN Y, SUN J X, YU H F, et al. Building multi-agent copilot towards autonomous agricultural data management and analysis[C]// 2024 IEEE International Conference on Big Data (BigData). Piscataway, New Jersey, USA: IEEE, 2024: 4384-4393.
[48]	WU Q Y, BANSAL G, ZHANG J Y, et al. Autogen: Enabling next-gen LLM applications via multi-agent conversation framework[EB/OL]. arXiv: 2308.08155, 2023.
[49]	SHI H R, LI S B, YUAN Z Y, et al. PestMA: LLM-based multi-agent system for informed pest management[EB/OL]. arXiv: 2504.09855, 2025.
[50]	CHEN Y J, ZHU K X, CHEN Z D, et al. Intelligent multi-agent systems for UAV-robot path optimization via reflective evolution[M]// Parallel and Distributed Computing, Applications and Technologies. Singapore: Springer Nature Singapore, 2025: 566-577.
[51]	THUDUMU S, FISHER J. OpenAg: Democratizing agricultural intelligence [EB/OL] arXiv: 2506.04571, 2025.
[52]	张浩, 蔡晨馨, 屈傲, 等. Beehive: 基于智能体的智慧农场操作系统[J]. 计算, 2025, 1(2): 63-70.
	ZHANG H, CAI C X, QU A, et al. Beehive: Agent-based smart farm operating system[J]. Computing magazine of the CCF, 2025, 1(2): 63-70.
[53]	刘海峰, 孟祥宝, 谢秋波, 等. 我国智能化植物工厂发展现状与对策建议[J]. 广东科技, 2021, 30(7): 69-71.
[54]	万欢, 欧媛珍, 管宪鲁, 等. 无人农机作业环境感知技术综述[J]. 农业工程学报, 2024, 40(8): 1-18.
	WAN H, OU Y Z, GUAN X L, et al. Review of the perception technologies for unmanned agricultural machinery operating environment[J]. Transactions of the Chinese society of agricultural engineering, 2024, 40(8): 1-18.
[55]	赵春江. 智慧农业发展现状及战略目标研究[J]. 智慧农业, 2019, 1(1): 1-7.
	ZHAO C J. State-of-the-art and recommended developmental strategic objectivs of smart agriculture[J]. Smart agriculture, 2019, 1(1): 1-7.
[56]	XU H, MAN Y B, YANG M Y, et al. Analytical insight of earth: A cloud-platform of intelligent computing for geospatial big data[EB/OL]. arXiv: 2312.16385, 2023.
[57]	WILLIAMS D, MACFARLANE F, BRITTEN A. Leaf only SAM: A segment anything pipeline for zero-shot automated leaf segmentation[J]. Smart agricultural technology, 2024, 8: ID 100515.
[58]	WANG L Q, JIN T, YANG J Y, et al. Agri-LLaVA: Knowledge-infused large multimodal assistant on agricultural pests and diseases[EB/OL]. arXiv: 2412.02158, 2024.
[59]	REZAYI S, LIU Z L, WU Z H, et al. AgriBERT: Knowledge-infused agricultural language models for matching food and nutrition[C]// the Thirty-First International Joint Conference on Artificial Intelligence AI for Good. Messe Wien, Vienna, Austria: IJCAI, 2022: 5150-5156.
[60]	YANG X J, GAO J F, XUE W X, et al. Pllama: An open-source large language model for plant science[EB/OL]. arXiv: 2401.01600, 2024.
[61]	赵春江, 李静晨, 吴华瑞, 等. 基于大语言模型推理的数字孪生平台蔬菜作物生长模型研究[J]. 智慧农业(中英文), 2024, 6(6): 63-71.
	ZHAO C J, LI J C, WU H R, et al. Vegetable crop growth modeling in digital twin platform based on large language model inference[J]. Smart agriculture, 2024, 6(6): 63-71.
[62]	任荣荣, 胡崇宇, 吴国龙. 农业种植智能体(Agri-agent)的构建与应用展望[J]. 农业展望, 2024, 20(6): 92-106.
	REN R R, HU C Y, WU G L. Construction and application outlook of agri-agent[J]. Agricultural outlook, 2024, 20(6): 92-106.
[63]	吴华瑞, 李晓锁. 大模型在设施蔬菜智能化生产中的应用[J]. 蔬菜, 2024(11): 1-8.
	WU H R, LI X S. Application of large model in intelligent production of protected vegetables[J]. Vegetables, 2024(11): 1-8.
[64]	LIU Z, LIU M J, CHEN J Z, et al. Fusion: Fully integration of vision-language representations for deep cross-modal[EB/OL]. arXiv: 2504.09925, 2025.
[65]	JIANG J C, LI Y, NIE J, et al. Integrating large language models with cross-modal data fusion for advanced intelligent transportation systems in sustainable cities development[J]. Applied soft computing, 2025, 177: ID 113278.
[66]	DU M N, LIU N H, HU X. Techniques for interpretable machine learning[J]. Communications of the ACM, 2019, 63(1): 68-77.
[67]	ZHAO H Y, CHEN H J, YANG F, et al. Explainability for large language models: A survey[J]. ACM transactions on intelligent systems and technology, 2024, 15(2): 1-38.
[68]	BLEVINS T, GONEN H, ZETTLEMOYER L. Prompting language models for linguistic structure[EB/OL]. arXiv: 2211.07830, 2022.
[69]	RIBEIRO M T, SINGH S, GUESTRIN C. "Why should I trust you": Explaining the predictions of any classifier[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA. ACM, 2016: 1135-1144.
[70]	LUNDBERG S M, LEE S I. A unified approach to interpreting model predictions[C]// 31st Conference on Neural Information Processing Systems. Red Hook, New York, USA: Curran Associates Inc., 2017: 4768-4777.
[71]	HUANG L, YU W J, MA W T, et al. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions[J]. ACM transactions on information systems, 2025, 43(2): 1-55.
[72]	张宇芹, 朱景全, 董薇, 等. 农业垂直领域大语言模型构建流程和技术展望[J]. 农业大数据学报, 2024, 6(3): 412-423.
	ZHANG Y Q, ZHU J Q, DONG W, et al. Construction process and technological prospects of large language models in the agricultural vertical domain[J]. Journal of agricultural big data, 2024, 6(3): 412-423.
[73]	BéCHARD P, AYALA O M. Reducing hallucination in structured outputs via Retrieval-Augmented Generation[EB/OL]. arXiv: 2404.08189, 2024.
[74]	MARTINO A, IANNELLI M, TRUONG C. Knowledge injection to counter large language model (LLM) hallucination[M]// The Semantic Web: ESWC 2023 Satellite Events. Cham: Springer Nature Switzerland, 2023: 182-185.
[75]	FELDMAN P, FOULDS J R, PAN S M. Trapping LLM hallucinations using tagged context prompts[EB/OL]. arXiv: 2306.06085, 2023.
[76]	WEI J H, YAO Y S, J-FTON, et al. Measuring and reducing LLM hallucination without gold-standard answers[EB/OL]. arXiv: 2402.10412, 2024.
[77]	BANERJEE S, AGARWAL A, SINGLA S. LLMs will always hallucinate, and we need to live with this[EB/OL]. arXiv: 2409.05746, 2024.

方法	MMLU	HumanEval	SRDD	CommonGen	平均分
测试集规模/条	14 042	164	1 201	1 497	平均分
GPTSwarm	0.236 8	0.496 9	0.709 6	0.622 2	0.516 3
AgentVerse	0.297 7	0.725 6	0.758 7	0.539 9	0.580 5
MacNet （链式结构）	0.663 2	0.372 0	0.805 6	0.590 3	0.607 8

多智能体大模型在农业中的应用研究与展望

Applications Research Progress and Prospects of Multi-Agent Large Language Models in Agricultural

在线阅读

知网下载

本地下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 77

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈程程, 吴佳平, 于合龙. 光智农业数据感知技术的前沿进展与发展趋势——从光学传感器到智能决策系统[J]. 智慧农业(中英文), 2025, 7(5): 1-16.
[2]	李汶政, 杨信廷, 孙传恒, 崔腾鹏, 王慧, 李珊珊, 李文勇. 联合空间深度转换卷积与多尺度注意力机制的灯诱稻飞虱害虫检测方法[J]. 智慧农业(中英文), 2025, 7(5): 169-181.
[3]	韩文凯, 李涛, 冯青春, 陈立平. 面向复杂果园环境的改进YOLOv11n苹果轻量化实例分割算法[J]. 智慧农业(中英文), 2025, 7(5): 114-123.
[4]	胡妍, 王玉洁, 张雪晨, 张熠强, 于桦昊, 宋馨蓓, 叶思潭, 周继红, 陈振林, 纵巍伟, 何勇, 李晓丽. 基于高光谱成像技术的茯砖茶发花品质无损检测与智能识别方法[J]. 智慧农业(中英文), 2025, 7(4): 71-83.
[5]	李瑞杰, 王爱冬, 吴华星, 李子秋, 冯向前, 洪卫源, 汤学军, 覃金华, 王丹英, 褚光, 张运波, 陈松. 水稻生育期遥感监测的研究进展、瓶颈问题与技术优化路径[J]. 智慧农业(中英文), 2025, 7(3): 89-107.
[6]	韩宇, 齐康康, 郑纪业, 李金瑷, 姜富贵, 张相伦, 游伟, 张霞. 基于改进YOLOv11的轻量化肉牛面部识别方法[J]. 智慧农业(中英文), 2025, 7(3): 173-184.
[7]	马六, 毛克彪, 郭中华. 基于混合注意力生成对抗网络的遥感图像去雾方法[J]. 智慧农业(中英文), 2025, 7(2): 172-182.
[8]	赵柄婷, 华传海, 叶晨洋, 熊育春, 钱涛, 程涛, 姚霞, 郑恒彪, 朱艳, 曹卫星, 江冲亚. 水稻生产遥感监测与智慧决策研究进展[J]. 智慧农业(中英文), 2025, 7(2): 57-72.
[9]	吴华瑞, 李静晨, 杨雨森. 基于大语言模型的个性化作物水肥管理智能决策方法[J]. 智慧农业(中英文), 2025, 7(1): 11-19.
[10]	许世卫, 李乾川, 栾汝朋, 庄家煜, 刘佳佳, 熊露. 农产品市场监测预警深度学习智能预测方法[J]. 智慧农业(中英文), 2025, 7(1): 57-69.
[11]	宫宇, 王玲, 赵荣强, 尤海波, 周沫, 刘劼. 基于多模态数据表型特征提取的番茄生长高度预测方法[J]. 智慧农业(中英文), 2025, 7(1): 97-110.
[12]	姜京池, 闫莲, 刘劼. 基于精准知识筛选及知识协同生成的农业大语言模型[J]. 智慧农业(中英文), 2025, 7(1): 20-32.
[13]	齐梓均, 牛当当, 吴华瑞, 张礼麟, 王仑峰, 张宏鸣. 基于双维信息与剪枝的中文猕猴桃文本命名实体识别方法[J]. 智慧农业(中英文), 2025, 7(1): 44-56.
[14]	吴华瑞, 赵春江, 李静晨. 基于多模态融合大模型架构Agri-QA Net的作物知识问答系统[J]. 智慧农业(中英文), 2025, 7(1): 1-10.
[15]	张辉, 胡军, 石航, 刘昶希, 吴淼. 融合远端深度学习识别模型的白菜株心精准对靶喷雾系统[J]. 智慧农业(中英文), 2024, 6(6): 85-95.