claude官方揭秘:为啥不需要多Agent架构?《Building multi-agent systems: when and how to use 》①
不同类型 Agent 怎么评估?四类 Agent 的评分器侧重点:Anthropic《Demystifying evals for AI agents》④
多agent系统:最不容易翻车的子 Agent 是谁?-《Building multi-agent systems: when and how to …》③
单体Agent起步,拒绝造火箭:Anthropic《Building Effective AI Agents: Architecture Patterns》①
Agent Teams 正在逼近什么样的未来?一个高度自主的工程时代:《Building a C compiler with a team of parall
Google总结了5种Skill设计模式,让Agent稳定输出
从原型实验出发,拆解 Claude Agent Teams 的基础架构:《Building a C compiler with a team…》①
Agent 评估工具要不要自建?如何理性选择框架:Anthropic《Demystifying evals for AI agents》⑦
多Agent:蜜糖还是砒霜?——claude《Building Effective AI Agents:Architecture Patterns and Im
为什么 Agent Memory 不是上下文工程的子集? Memory in the Age of AI Agents》③
多Agent评估体系:从小样本测试、自动化裁判到人类兜底:精读《How we built our multiagent research system》④
挑战12分钟搞定,多智能体(Multi-Agent)架构
Agent架构选型:好架构都是逼出来的|claude《Building Effective AI Agents:Architecture Patterns》④
多智能体架构全景-主agent如何动态派生subagent:精读《How we built our multi-agent research system》②
没有评估的 Agent,注定不可规模化:Anthropic《Demystifying evals for AI agents》①
给大家推荐三个超好用的skills
如何从0到1打造自己的agent评估体系:Anthropic《Demystifying evals for AI agents》⑤
区分agent framework与agent harness
Workflow模式之:Prompt Chaining-为什么单LLM能做的任务,偏要拆开? | 精读《Building Effective Agents》③
构建agent的原子能力-增强型LLM:精读《Building effective agents》②