2025年Agents与基础应用白皮书 英文版 .docxVIP

Agents

Authors:JuliaWiesinger,PatrickMarlowandVladimirVuskovic

Agents

Acknowledgements

ReviewersandContributors

EvanHuang

EmilyXue

OlcanSercinoglu

SebastianRiedel

SatinderBaveja

AntonioGulli

AnantNawalgaria

CuratorsandEditors

AntonioGulli

AnantNawalgaria

GraceMollison

TechnicalWriter

JoeyHaymaker

Designer

MichaelLanning

September2024 2

Tableofcontents

Introduction 4

Whatisanagent? 5

Themodel 6

Thetools 7

Theorchestrationlayer 7

Agentsvs.models 8

Cognitivearchitectures:Howagentsoperate 8

Tools:Ourkeystotheoutsideworld 12

Extensions 13

SampleExtensions 15

Functions 18

Usecases 21

Functionsamplecode 24

Datastores 27

Implementationandapplication 28

Toolsrecap 32

Enhancingmodelperformancewithtargetedlearning 33

AgentquickstartwithLangChain 35

ProductionapplicationswithVertexAIagents 38

Summary 40

Endnotes 42

Agents

Thiscombinationofreasoning,logic,andaccesstoexternalinformationthatareallconnectedtoaGenerativeAImodelinvokestheconceptofanagent.

Introduction

Humansarefantasticatmessypatternrecognitiontasks.However,theyoftenrelyontools-likebooks,GoogleSearch,oracalculator-tosupplementtheirpriorknowledgebeforearrivingataconclusion.Justlikehumans,GenerativeAImodelscanbetrainedtousetoolstoaccessreal-timeinformationorsuggestareal-worldaction.Forexample,amodelcan

leverageadatabaseretrievaltooltoaccessspecificinformation,likeacustomerspurchasehistory,soitcangeneratetailoredshoppingrecommendations.Alternatively,basedonausersquery,amodelcanmakevariousAPIcallstosendanemailresponsetoacolleagueorcompleteafinancialtransactiononyourbehalf.Todoso,themodelmustnotonlyhaveaccesstoasetofexternaltools,itneedstheabilitytoplanandexecuteanytaskinaself-directedfashion.Thiscombinationofreasoning,logic,andaccesstoexternalinformationthatareallconnectedtoaGen