摘要
随着大语言模型技术的高速发展,对话式AI已取得显著进展,但在更复杂任务执行与决策层面仍显局限.为此,代理智能因致力于突破大语言模型仅限信息处理的瓶颈而日益受到关注.文中提出基于代理智能技术的平行厨师智能烹饪系统,提供从菜品决策到烹饪执行的全流程智能化方案.系统综合利用用户健康数据、病史与饮食偏好,实现个性化的菜谱设计与烹饪控制.基于DeepSeek构建多智能体,从烹饪文献提炼专业问答,对大语言模型离线微调,使其具备烹饪推理能力.仿真实验表明,相比推理能力较强的静态大模型GPT o1 pro,代理智能方案融入更丰富的专业知识,更贴合用户需求,凸显出其在健康饮食与个性化服务中的应用潜力.
Progress is made by conversation-based AI due to the rapid development of large language models(LLMs).However,limitations still remain in performing more complex tasks and decision-making.Therefore,agentic intelligence is increasingly emphasized to address the bottleneck that LLMs are confined to information processing.In this paper,a parallel chef cooking system based on agentic intelligence is presented to offer an end-to-end intelligent approach from dish planning to cooking execution.User health data,medical history,and dietary preferences are incorporated to enable personalized recipe design and cooking control.In addition,multi-agent structures are built upon the DeepSeek framework,and specialized Q&A pairs are extracted from culinary literature to offline fine-tune the large language model,thereby imparting cooking reasoning capabilities.Simulation experiments show that compared to GPT o1 pro,a static large model with strong reasoning ability,the agentic approach integrates more extensive professional knowledge and better meets user requirements,showcasing its potential in dietary health and personalized cooking services.
作者
李柏
宋秭函
李鑫源
黄峻
田永林
殷烛炎
王飞跃
LI Bai;SONG Zihan;LI Xinyuan;HUANG Jun;TIAN Yonglin;YIN Zhuyan;WANG Fei-Yue(College of Mechanical and Vehicle Engineering,Hunan University,Changsha 410082;State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle,Hunan University,Changsha 410082;Department of Engineering Science,Faculty of Innovation Engineering,Macao University of Science and Technology,Macao 999078;State Key Laboratory of Multi-modal Artificial Intelligence Sys-tems,Institute of Automation,Chinese Academy of Sciences,Beijing 100190;State Key Laboratory for Management and Control of Complex Systems,Institute of Automation,Chinese Academy of Sciences,Beijing 100190;School of Artificial Intelligence,University of Chinese Academy of Sciences,Beijing 100049)
出处
《模式识别与人工智能》
北大核心
2025年第3期252-267,共16页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金项目(No.62103139)
湖南省芙蓉计划湖湘青年英才项目(No.2023RC3115)资助。
关键词
AI智能体
代理智能
平行智能
大语言模型
烹饪机器人
智能烹饪
AI Agent
Agentic Intelligence
Parallel Intelligence
Large Language Model
Cooking Robot
Intelligent Cooking
作者简介
李柏,博士,副教授,主要研究方向为自主无人系统运动规划和最优控制.E-mail:libai@zju.edu.cn;宋秭函,硕士研究生,主要研究方向为基于代理智能的自主无人系统决策规划与控制.E-mail:songzihan@hnu.edu.cn;李鑫源,硕士研究生,主要研究方向为大语言模型、具身智能、柔性机械臂建模与控制.E-mail:lixinyuan99@hnu.edu.cn;黄峻,博士研究生,主要研究方向为平行智能、自动驾驶轨迹预测规划、提示工程、大语言模型等.E-mail:junhuang@ieee.org;田永林,博士,助理研究员,主要研究方向为平行系统、自动驾驶、场景工程.E-mail:yonglin.tian@ia.ac.cn;殷烛炎,学士,科研助理,主要研究方向为运筹优化、智能控制、多模态大语言模型.E-mail:1026078242@qq.com;通信作者:王飞跃,博士,研究员,主要研究方向为平行系统的方法与应用、社会计算、平行智能、知识自动化.E-mail:feiyue.wang@ia.ac.cn.
