跳到正文
AI NEWS JOURNAL
AI, IN PERSPECTIVE

搜索 AI 资讯

检索标题、摘要与正文,把分散的信息连起来。

按发布时间排序

n8n@3.0.0

# [3.0.0](https://github.com/n8n-io/n8n/compare/n8n@2.45.0...n8n@3.0.0)(2026-10-27)### 问题修复 * 在工件下载按钮上添加文件类型提示工具提示([#41490](https://github.com/n8n-io/n8n/issues/41490))([4a74f02](https://github.com/n8n-io/n8n/commit/4a74f027e612f31098b354dd3a77b2c2ab98281c)) * **ai-builder:** 检查执行权限:在 Assistant 执行读取时进行检查([#41863](https://github.com/n8n-io/n8n/issues/41863))([a967486](https://github.com/n8n-io/n8n/commit/a9674866d075e989a5ce896432262c9a7dc8b0c7)) * **ai-builder:** 通过已配置的 AI 传输通道发送 Assistant 模型调用([#41948](https://github.com/n8n-io/n8n/issues/41948))([9b63561](https://github.com/n8n-io/n8n/commit/9b63561cbb48f06d216f27be3b77722d97e4e74a)) * 支持自定义 OAuth2 范围([#41249](https://github.com/n8n-

事件进展与其他报道

n8n@2.46.0

# [2.46.0](https://github.com/n8n-io/n8n/compare/n8n@2.45.0...n8n@2.46.0)(2026-10-27)### 修复的缺陷 * 在工件下载按钮上添加文件类型提示工具提示([#41490](https://github.com/n8n-io/n8n/issues/41490))([4a74f02](https://github.com/n8n-io/n8n/commit/4a74f027e612f31098b354dd3a77b2c2ab98281c)) * **ai-builder:** 检查执行权限:在 Assistant 执行读取操作时进行检查([#41863](https://github.com/n8n-io/n8n/issues/41863))([a967486](https://github.com/n8n-io/n8n/commit/a9674866d075e989a5ce896432262c9a7dc8b0c7)) * **ai-builder:** 通过已配置的 AI 传输通道发送 Assistant 模型调用([#41948](https://github.com/n8n-io/n8n/issues/41948))([9b63561](https://github.com/n8n-io/n8n/commit/9b63561cbb48f06d216f27be3b77722d97e4e74a)) * 支持自定义 OAuth2 范围([#41249](https://github.com/n8

事件进展与其他报道

SAP凭借更智能、受治理的Joule代理,进一步推进其自主企业战略

SAP SE 今日在其面向开发者的年度 TechEd 大会上宣布了一系列人工智能创新,进一步强化了其 Joule 智能体解决方案和 Business AI 平台,其中包括表格数据基础模型。Joule Work 的新功能将助力 AI 智能体提升效率,并与开放协议实现互操作。在此背景下,模型上下文协议[…] 该文章“SAP 以更智能、受管的 Joule 智能体推动企业自主化发展”首发于 SiliconANGLE。

事件进展与其他报道

把15个国民级App接入灵光后,我造出了最舒适的国产Personal Agent

自从拿到蚂蚁灵光2.0这个Personal Agent的内测,它已经成为我的私人管家了。到现在,我已经通过Skill、MCP、GitHub项目或者内置的方式,把15个国民级App都接进去了。基本上我打开「帮我管」那一栏里,定时任务里会定时刷新值得关注的信息。灵光不是我用的第一个Personal Agent,前前后后一共测了12个,测到后面,我越来越觉...

把15个国民级App接入灵光后,我造出了最舒适的国产Personal Agent
事件进展与其他报道

v0.43.0

## 有哪些变化 * model_prefetch:由 @rattus128 在 https://github.com/Comfy-Org/ComfyUI/pull/17178 中同步所有图的清理操作 * 由 @kijai 在 https://github.com/Comfy-Org/ComfyUI/pull/17172 中为 MOSS-image 添加绳索缩放支持 * [合作伙伴节点] 由 @dante01yoon 在 https://github.com/Comfy-Org/ComfyUI/pull/16943 中更新 API 节点中的合作伙伴节点登录令牌 * [合作伙伴节点] 功能(HeyGen):由 @bigcat88 在 https://github.com/Comfy-Org/ComfyUI/pull/17043 中添加 HeyGen Voice 即时克隆与文本转语音功能 * [合作伙伴节点] 功能(ClarityAI):由 @bigcat88 在 https://github.com/Comfy-Org/ComfyUI/pull/17192 中添加 Crystal 视频超分辨率节点 * [合作伙伴节点] 功能(BFL):由 @bigcat88 在 https://github.com/Comfy-Org/ComfyUI/pull/17200 中为 FLUX 3 视频节点新增 2K/4K 分辨率支持 * 支持 MOSS-image

事件进展与其他报道

beta

## [2.45.4](https://github.com/n8n-io/n8n/compare/n8n@2.45.3...n8n@2.45.4) (2026-10-26) ### Bug Fixes * **core:** Recreate removed n8n-sandbox sandboxes and rerun workspace setup ([#41919](https://github.com/n8n-io/n8n/issues/41919)) ([11e279a](https://github.com/n8n-io/n8n/commit/11e279a51d497f8d96f5f9f90bb314dda4f6a49e)) * **core:** Start sub-workflow error workflow when a pre-run check fails ([#41977](https://github.com/n8n-io/n8n/issues/41977)) ([9595142](https://github.com/n8n-io/n8n/commit/95951428c765f3f0b1da9f341a6ab8c75673385a)) * **editor:** Match navigation plus button hover styling ([#41910](https://github.com/n8n-io/n8n/issues/41910)) ([471c006](https://github.com/n8n-io/n8n/commit/471c006fdd46091659f3e1d28d989702049489f0)) * **editor:** Point migration report docs link to the

译文排队中,当前为原文 · en
事件进展与其他报道

n8n@2.45.4

## [2.45.4](https://github.com/n8n-io/n8n/compare/n8n@2.45.3...n8n@2.45.4) (2026-10-26) ### Bug Fixes * **core:** Recreate removed n8n-sandbox sandboxes and rerun workspace setup ([#41919](https://github.com/n8n-io/n8n/issues/41919)) ([11e279a](https://github.com/n8n-io/n8n/commit/11e279a51d497f8d96f5f9f90bb314dda4f6a49e)) * **core:** Start sub-workflow error workflow when a pre-run check fails ([#41977](https://github.com/n8n-io/n8n/issues/41977)) ([9595142](https://github.com/n8n-io/n8n/commit/95951428c765f3f0b1da9f341a6ab8c75673385a)) * **editor:** Match navigation plus button hover styling ([#41910](https://github.com/n8n-io/n8n/issues/41910)) ([471c006](https://github.com/n8n-io/n8n/commit/471c006fdd46091659f3e1d28d989702049489f0)) * **editor:** Point migration report docs link to the

译文排队中,当前为原文 · en
事件进展与其他报道

stable

## [2.44.7](https://github.com/n8n-io/n8n/compare/n8n@2.44.6...n8n@2.44.7) (2026-10-26) ### Bug Fixes * **core:** Start sub-workflow error workflow when a pre-run check fails ([#41978](https://github.com/n8n-io/n8n/issues/41978)) ([67d0e65](https://github.com/n8n-io/n8n/commit/67d0e65f5d5d01d49b1d14ea2c26a6b803bf058b)) * **Email Trigger (IMAP) Node:** Back off reconnects when the server drops each new connection ([#41927](https://github.com/n8n-io/n8n/issues/41927)) ([10a9518](https://github.com/n8n-io/n8n/commit/10a9518f0d9d470e619b500383b5b76fc1870662)) * **Microsoft SharePoint Node:** Fix the column mapper 403 and empty items in Map Automatically ([#41906](https://github.com/n8n-io/n8n/issues/41906)) ([e67d278](https://github.com/n8n-io/n8n/commit/e67d278ef0ae3c15493e74813ecce972e384ff1

译文排队中,当前为原文 · en
事件进展与其他报道

n8n@2.44.7

## [2.44.7](https://github.com/n8n-io/n8n/compare/n8n@2.44.6...n8n@2.44.7) (2026-10-26) ### Bug Fixes * **core:** Start sub-workflow error workflow when a pre-run check fails ([#41978](https://github.com/n8n-io/n8n/issues/41978)) ([67d0e65](https://github.com/n8n-io/n8n/commit/67d0e65f5d5d01d49b1d14ea2c26a6b803bf058b)) * **Email Trigger (IMAP) Node:** Back off reconnects when the server drops each new connection ([#41927](https://github.com/n8n-io/n8n/issues/41927)) ([10a9518](https://github.com/n8n-io/n8n/commit/10a9518f0d9d470e619b500383b5b76fc1870662)) * **Microsoft SharePoint Node:** Fix the column mapper 403 and empty items in Map Automatically ([#41906](https://github.com/n8n-io/n8n/issues/41906)) ([e67d278](https://github.com/n8n-io/n8n/commit/e67d278ef0ae3c15493e74813ecce972e384ff1

译文排队中,当前为原文 · en
事件进展与其他报道

DraMaze:一种具备未来感知记忆的多智能体流水线,用于多样化的微剧剧本生成

arXiv:2610.32002v1 发布类型:新 摘要:微剧的迅猛发展使得对高质量剧本创作的需求日益增长。利用大语言模型进行长篇微剧剧本生成,既需要多样化的剧情推进,又要求具备长时段的叙事连贯性。我们的观察表明,随着生成过程的推进,候选续写内容越来越倾向于聚焦于少数几种叙事机制;而传统的检索方式则可能加剧套路的重复使用,并忽视对未来情节至关重要的历史信息。为应对这些挑战,我们提出了DraMaze,这是一种多智能体流水线,通过基于套路记忆的进化树搜索与变异机制,探索多样化的因果路径;同时,它还构建了逆向叙事依赖树,用于组织、保存并检索历史记忆。

事件进展与其他报道

Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows

arXiv:2610.31916v1 Announce Type: new Abstract: A durable agent can resume a consequential action while its authority changes and the action's external outcome remains uncertain. We study execution-time reliability of tool-using AI agents, isolating recovery decisions from language-model behavior. Checkpoint state, permission to dispatch, evidence of an external effect and permission to reconcile are distinct obligations. We present a finite conformance study that checks these obligations through histories scored against a provider effect ledger hidden from the recovering application. A prospectively frozen campaign executes 336 histories on native LangGraph and Temporal hosts, crossing 14 schedules, three provider contracts and four matched application policies. All 168 paired host cells

译文排队中,当前为原文 · en
Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows
事件进展与其他报道

Understanding Communication Failures in Multi-Agent LLM Systems

arXiv:2610.32060v1 Announce Type: new Abstract: Multi-agent LLM systems aim to improve reasoning through debate, evidence sharing, and mutual correction, but interaction can also introduce failures that final accuracy alone cannot explain. Agents may converge too early, ignore dissent, suppress correct minority answers, or preserve a wrong framing across rounds. We present a corpus-grounded taxonomy of communication failures, built from 3,211 failed multi-round trajectories across medical QA, coding, finance, multi-hop reasoning, ethics, and embodied text tasks. Using this taxonomy, we analyze failure distributions across datasets and system designs, round-level error dynamics, recovery hardness, majority transitions, minority-signal suppression, and self-reported confidence. We find that

译文排队中,当前为原文 · en
事件进展与其他报道

LangChain发布“公司级智能体框架”五大核心组件

LangChain于2026年10月25日发布博客,系统阐述其在营销、销售与工程团队内部部署AI智能体(GTM Agent、OpenSWE、Content Studio)所沉淀的五大通用架构原则:原生集成工作环境(Slack)、动态身份模型(OBO+固定凭证)、双层记忆机制(全局/用户级)、沙箱化代码执行、高比例调度运行(非手动触发)。所有智能体均基于Managed Deep Agents平台构建。

推荐理由:该资讯源自LangChain官方博客,发布时间(2026-10-25T18:06:32.000Z)早于当前系统时间(2026-10-25T23:01:18.857Z),内容聚焦已落地的内部智能体实践,细节具体(如Slack线程隔离、GitHub账号归属逻辑、Notion/Twitter权限分层等),未含未经验证的预测或外部宣称,符合时效性与事实性要求。

事件进展与其他报道

微软开源Agensh:支持1024个自主协作AI编码代理的去中心化框架

微软研究院于2026年10月25日开源Agensh,一种无需中央协调器的多代理运行时框架,支持1至1024个LLM编码代理在ProgramBench上自组织协作。系统基于Gitea、Mattermost和DeLM风格共享看板实现去中心化协调,所有代理运行同一提示驱动的五步循环,已在Linux+Docker环境下验证可扩展性。

Microsoft Open-Sources Agensh: A Multi-Agent Harness for 1,024 Agents

推荐理由:该成果代表多智能体系统架构的重要演进——摒弃传统‘主控代理’范式,通过提示工程与轻量服务组合实现大规模自组织;其在ProgramBench上的实证数据(如128代理使5任务均分提升49%)为分布式AI工程提供新基准;MIT许可证开源且兼容Copilot CLI等主流单代理工具,具备实际开发参考价值。

事件进展与其他报道