elvis@omarsar0
42AI 编辑部评分,满分 100
2026-08-01 22:13· 31分钟前
跳到正文
AI 摘要

DAIR.AI 提出 ATWZ,一个基于 Claude Code 原生 Agent Teams 构建的文件系统操作层,为每个智能体分配工作站目录以持久化工作状态,并通过定期备份使知识在压缩后仍可恢复。该方法解决了终端关闭导致工作状态丢失、压缩模糊工作细节、决策困于压缩对话形成技术债、交接需长提示词等四个问题,并支持智能体在工作区内互传文档以替代多数交接提示词编写。

// Persistent Workspaces for Long-Lived Claude Code Agent Teams //

Four issues to be aware of:

Working state vanishes when a terminal closes and the team cannot be resumed.

Compaction condenses the conversation and blurs each agent's working detail.

Decisions and operations get trapped in compacted chats, which accumulates as agentic technical debt.

Every handoff needs another long prompt.

ATWZ is a filesystem operations layer built around Claude Code's native Agent Teams. Each agent gets a workstation directory holding its working state alongside the skills, hooks and scripts that maintain those files. The team backs up periodically so knowledge survives compaction, and a single command restores the whole team after the process ends.

Agents also send documents to one another inside the workspace, which replaces most of the handoff prompt writing.

Paper: https://arxiv.org/abs/2607.22917

Track more trending AI papers in our academy: https://academy.dair.ai/

elvis · @omarsar0 · X·2026-08-01 22:13·31分钟前
在 X 看原推· x.com
AI 摘要

DAIR.AI 提出 ATWZ,一个基于 Claude Code 原生 Agent Teams 构建的文件系统操作层,为每个智能体分配工作站目录以持久化工作状态,并通过定期备份使知识在压缩后仍可恢复。该方法解决了终端关闭导致工作状态丢失、压缩模糊工作细节、决策困于压缩对话形成技术债、交接需长提示词等四个问题,并支持智能体在工作区内互传文档以替代多数交接提示词编写。

// Persistent Workspaces for Long-Lived Claude Code Agent Teams //

Four issues to be aware of:

Working state vanishes when a terminal closes and the team cannot be resumed.

Compaction condenses the conversation and blurs each agent's working detail.

Decisions and operations get trapped in compacted chats, which accumulates as agentic technical debt.

Every handoff needs another long prompt.

ATWZ is a filesystem operations layer built around Claude Code's native Agent Teams. Each agent gets a workstation directory holding its working state alongside the skills, hooks and scripts that maintain those files. The team backs up periodically so knowledge survives compaction, and a single command restores the whole team after the process ends.

Agents also send documents to one another inside the workspace, which replaces most of the handoff prompt writing.

Paper: https://arxiv.org/abs/2607.22917

Track more trending AI papers in our academy: https://academy.dair.ai/

在 X 查看原推x.com