Patterns and problems in multiagent systems
We ran experiments on swarms of Claude agents and found coordination failures, collusion, and sabotage. Here, we share what they mean for AI safety.
Topic
#agent-patterns
7 篇笔记
最佳实践：从Multi-Agent到Agent Team
2w字长文，Agent Team 的最佳实践。
Codex 进阶指南：作为 Multi-Agent 编排控制平面
大多数人用 Codex 的方式，是开一个会话、交代一件事、等它做完。这种用法只动用了它很小一部分能力。Codex 真正提供的是一组完整的调度原语：发现有哪些项目和会话、创建新会话、从已有会话分叉、给别的会话派活、等它们回来、观察它们的进展、纠正跑偏的那个、把任务搬到另一台机器、最...
多模型路由进入 Agent 会话之后
模型路由在单轮问答中可以按难度分配成本，但进入 Agent 多轮会话后，还要处理上下文、工具状态、缓存和隐式状态。本文拆解会话级路由的智能与工程瓶颈，以及固定强模型、隔离子任务和有状态路由三条现实路线。
Practical multi-agent orchestration in Codex
GPT-5.6 Sol gets especially interesting when it has a team to work with. Codex's new Multi-Agent V2 tools give Sol and Terra a natural way t...
A Taxonomy of Self-evolving Agents
Self-evolving agents are becoming popular. [Hermes Agent](https://hermes-agent.nousresearch.com/docs/user-guide/features/skills) enables aut...
15 AI Agent Design Patterns Every Engineer Must Know
Every team building AI agents hits the same wall.You start with one prompt and a few tools.It works. Then requirements grow. More edge cases...