苏震巍-协同研发的流程重塑：使用 AgentManager 打造多智能体 Copilot.pdf

1、协同研发的流程重塑：使用协同研发的流程重塑：使用 AgentManagerAgentManager 打造多智能体打造多智能体 Copilot Copilot 演讲人：苏震巍 香港理工大学人工智能方向博士研究生，主攻人工智能、数据挖掘、电子商务、信息管理获国际奖项：Microsoft Regional Director（RD）微软最有价值专家（MVP）腾讯云最有价值专家（TVP）机械工业出版社专家委员会委员 江苏省司法厅电子数据鉴定人 微软技术俱乐部（苏州）主席 苏州市人工智能学会理事 QCon、微软 Ignite、TechSummit 等技术大会讲师创始人&首席架构师：苏震巍（Jeffrey

2、Su）当前常见开发方式瀑布式敏捷传统开发流程普遍存在的问题 协同开发过程中的高度耦合（人、技术、信息）信息孤岛 沟通障碍 边界不清晰 整体交付效率低下Multi-Agent 概念AutoGenAutoGen:Enabling Next:Enabling Next-Gen LLMGen LLMApplications via MultiApplications via Multi-Agent Agent ConversationConversationhttps:/arxiv.org/abs/2308.08155关于 AI/Agent 的专访交流和分享https:/ https:/ 基本工作原理

3、Multi-Agent 工作流举例 An example workflow to address code-based question answering in supply-chain optimization(opens in new tab).The Commander receives user questions and coordinates with the Writer and Safeguard.The Writer crafts the code and interpretation,the Safeguard ensures safety,and the Command

4、er executes the code.If issues arise,the process can repeat until resolved.Shaded circles represent steps that may be repeated multiple times.Performance on four applications A1-A4.(a)shows that AutoGen agents can be used out of the box to achieve the most competitive performance on math problem sol

5、ving tasks;(b)shows that AutoGen can be used to realize effective retrieval augmentation and realize a novel interactive retrieval feature to boost performance on Q&A tasks;(c)shows that AutoGen can be used to introduce a three-agent system with a grounding agent to improve performance on ALFWorld;(

6、d)shows that a multi-agent design is helpful in boosting performance in coding tasks that need safeguards.Multi-Agent 工作流举例 An example of a new application enabled by AutoGen:conversational chess(opens in new tab).It can support various scenarios,as each player can be an LLM-empowered AI,a human,or