Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

PestMA: LLM-based Multi-Agent System for Informed Pest Management

Hongrui Shi, Shunbao Li, Zhipeng Yuan, Po Yang

TL;DR

This work tackles the challenge of delivering reliable, context-aware pest management recommendations by introducing PestMA, an LLM-based multi-agent system with an editorial workflow comprising an Editor, Retriever, and Validator. The approach enables specialized roles and external knowledge integration to produce and validate pest management decisions (PMD). Empirical results on 68 UK pest scenarios show initial PMD accuracy of 86.8%, rising to 92.6% after Validator validation, illustrating the value of collaborative agent-based reasoning and verification. The study underscores the potential of MAS-enabled LLMs to automate and improve pest management while highlighting avenues for future work, such as integrating retrieval-augmented generation and expanding evaluations beyond PMD.

Abstract

Effective pest management is complex due to the need for accurate, context-specific decisions. Recent advancements in large language models (LLMs) open new possibilities for addressing these challenges by providing sophisticated, adaptive knowledge acquisition and reasoning. However, existing LLM-based pest management approaches often rely on a single-agent paradigm, which can limit their capacity to incorporate diverse external information, engage in systematic validation, and address complex, threshold-driven decisions. To overcome these limitations, we introduce PestMA, an LLM-based multi-agent system (MAS) designed to generate reliable and evidence-based pest management advice. Building on an editorial paradigm, PestMA features three specialized agents, an Editor for synthesizing pest management recommendations, a Retriever for gathering relevant external data, and a Validator for ensuring correctness. Evaluations on real-world pest scenarios demonstrate that PestMA achieves an initial accuracy of 86.8% for pest management decisions, which increases to 92.6% after validation. These results underscore the value of collaborative agent-based workflows in refining and validating decisions, highlighting the potential of LLM-based multi-agent systems to automate and enhance pest management processes.

PestMA: LLM-based Multi-Agent System for Informed Pest Management

TL;DR

This work tackles the challenge of delivering reliable, context-aware pest management recommendations by introducing PestMA, an LLM-based multi-agent system with an editorial workflow comprising an Editor, Retriever, and Validator. The approach enables specialized roles and external knowledge integration to produce and validate pest management decisions (PMD). Empirical results on 68 UK pest scenarios show initial PMD accuracy of 86.8%, rising to 92.6% after Validator validation, illustrating the value of collaborative agent-based reasoning and verification. The study underscores the potential of MAS-enabled LLMs to automate and improve pest management while highlighting avenues for future work, such as integrating retrieval-augmented generation and expanding evaluations beyond PMD.

Abstract

Effective pest management is complex due to the need for accurate, context-specific decisions. Recent advancements in large language models (LLMs) open new possibilities for addressing these challenges by providing sophisticated, adaptive knowledge acquisition and reasoning. However, existing LLM-based pest management approaches often rely on a single-agent paradigm, which can limit their capacity to incorporate diverse external information, engage in systematic validation, and address complex, threshold-driven decisions. To overcome these limitations, we introduce PestMA, an LLM-based multi-agent system (MAS) designed to generate reliable and evidence-based pest management advice. Building on an editorial paradigm, PestMA features three specialized agents, an Editor for synthesizing pest management recommendations, a Retriever for gathering relevant external data, and a Validator for ensuring correctness. Evaluations on real-world pest scenarios demonstrate that PestMA achieves an initial accuracy of 86.8% for pest management decisions, which increases to 92.6% after validation. These results underscore the value of collaborative agent-based workflows in refining and validating decisions, highlighting the potential of LLM-based multi-agent systems to automate and enhance pest management processes.

Paper Structure

This paper contains 13 sections, 1 equation, 1 figure, 7 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. LLM-based Multi-Agent Systems
  4. LLM-based Pest Management
  5. Methodology
  6. Initialising PMA.
  7. Customising PMA.
  8. Validating PMA.
  9. Experiments and Results
  10. Dataset and Evaluation
  11. Agent and Task Profiling
  12. Results
  13. Conclusion

Figures (1)

  • Figure 1: The workflow of PestMA. Three agents--Editor, Retriever, and Validator--collaboratively generate the pest management advice given a pest management scenario requested by the user. Editor is responsible for synthesising the pest management advice, Retriever is tasked to find knowledge gaps in the PMA and search relevant information to fill the knowledge gaps, and the Validator accesses the PMA to ensure its accuracy and reliability.