交通信息与安全2026，Vol.44Issue(1)：13-25,13.DOI:10.3963/j.jssn.1674-4861.2026.01.002
基于大语言模型的海上搜救决策智能体建模方法
A Modeling Method of Large Language Model-based Decision-making Agents for Maritime Search and Rescue
摘要
Abstract
Current maritime search and rescue(SAR)decision-making faces challenges in unified semantic model-ing for multi-source heterogeneous information.This deficiency hinders joint reasoning across cross-modal data.Meanwhile,SAR missions involve multi-objective constraints with significant coupling between disparate decision goals.Traditional methods often rely on stage-wise or heuristic-driven processing.They lack the capacity for holis-tic reasoning and dynamic optimization within the multi-objective decision-making process.To address these chal-lenges,this paper investigates a modeling methodology for the intelligent search and rescue agent(IS-Res-cueAgent),This agent utilizes a large language model(LLM)as the core reasoning engine.By implementing the model context protocol(MCP),the framework achieves semantic-level coordination of cross-modal information.It executes closed-loop reasoning and multi-objective optimization within a unified process.Through collaborative mechanisms like problem identification and information parsing,the agent achieves fusion of cross-modal data.This includes distress messages,environmental data,and historical records.It also enables dynamic optimization for ves-sel scheduling,search paths,and task priorities.Architecturally,the proposed agent comprises three stages:First,the information processing stage achieves unified representation of cross-modal features through semantic extraction and intent recognition.Second,The strategy generation stage constructs a multi-objective optimization framework for scenario-adaptive plan generation.Finally,the learning stage establishes an iterative mechanism through perfor-mance feedback and parameter updates.Experimental results show that IS-RescueAgent achieves a relevance of 93%,an accuracy of 92%,and a rationality of 92.3%.These metrics outperform traditional LLM and Retrieval-Aug-mented Generation(RAG)approaches.Furthermore,the system demonstrates strong stability under environmental disturbances.Under conditions of wind speeds below 10 m/s and resource availability above 70%,error rates remain within 5%.The system also maintains high response efficiency with positioning errors under 10 m and communica-tion delays below 200 ms.关键词
海事搜救/大语言模型/智能体/辅助决策Key words
search and rescue(SAR)/large language model(LLM)/agent/auxiliary decision-making分类
交通工程引用本文复制引用
索永峰,罗芳芳,崔磊,王建明,潘学清..基于大语言模型的海上搜救决策智能体建模方法[J].交通信息与安全,2026,44(1):13-25,13.基金项目
国家自然科学基金项目(42501422)、对外合作项目(2025I0018)、厦门市自然科学基金项目(3502Z202473059、3502Z202573055)资助 （42501422）
