谷歌：2025年Agents与基础应用白皮书（英文版）（42页）.pdf

1、AgentsAuthors:Julia Wiesinger,Patrick Marlow and Vladimir VuskovicAgents2September 2024AcknowledgementsReviewers and ContributorsEvan HuangEmily XueOlcan SercinogluSebastian RiedelSatinder BavejaAntonio GulliAnant NawalgariaCurators and EditorsAntonio GulliAnant NawalgariaGrace Mollison Technical Wr

2、iterJoey HaymakerDesignerMichael Lanning Introduction 4What is an agent?5 The model 6 The tools 7 The orchestration layer 7 Agents vs.models 8 Cognitive architectures:How agents operate 8Tools:Our keys to the outside world 12 Extensions 13 Sample Extensions 15 Functions 18 Use cases 21 Function samp

3、le code 24 Data stores 27 Implementation and application 28 Tools recap 32Enhancing model performance with targeted learning 33Agent quick start with LangChain 35Production applications with Vertex AI agents 38Summary 40Endnotes 42Table of contentsAgents4September 2024IntroductionHumans are fantasti

4、c at messy pattern recognition tasks.However,they often rely on tools-like books,Google Search,or a calculator-to supplement their prior knowledge before arriving at a conclusion.Just like humans,Generative AI models can be trained to use tools to access real-time information or suggest a real-world

5、 action.For example,a model can leverage a database retrieval tool to access specific information,like a customers purchase history,so it can generate tailored shopping recommendations.Alternatively,based on a users query,a model can make various API calls to send an email response to a colleague or

6、 complete a financial transaction on your behalf.To do so,the model must not only have access to a set of external tools,it needs the ability to plan and execute any task in a self-directed fashion.This combination of reasoning,logic,and access to external information that are all connected to a Gen