从"控制流所有权"这一第一性原理出发，拆解 Workflow（DAG 编排、确定性执行）与 Agent（ReAct 循环、涌现式控制流）的技术原理差异；详解 Agentic Workflow"图做骨架、节点内自主"的三层混合架构，以及提示链/路由/并行化/编排者-执行者/评审-优化五种经典编排模式与工程选型经验。

Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through …

Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in long, …

Armin Ronacher 发表《Pi: The Minimal Agent Within OpenClaw》，系统阐述了 Pi 框架'四个工具 + 最短系统提示词'的极简主义 Agent 设计观。

In this work, we present Gander, an end-to-end model that unifies omni perception, realtime interaction, and agentic cap…

LLM agents are rapidly becoming production software, deployed to handle customer service, adjudicate disputes, and opera…

Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon …

截至 2026 年 9 月，Pi 智能体框架 GitHub Star 突破 86k，pi-ai / pi-agent-core / pi-tui 组件被大量第三方 Agent 项目复用，'自建 Agent 而非套框架'成为新潮流。

谁能成为真正的「国民级AI 办公助理」 #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：ifanr），更多精彩内容第一时间为您奉上。

Benchmarks for the side effects an agent causes on the way to a goal already exist, but HarvestBench is the first to put…

中国团队 Monica 发布通用智能体产品 Manus，以'Less Structure, More Intelligence'理念实现任务全自动执行，在 GAIA 基准取得 SOTA 表现，一码难求。

IT之家 9 月 9 日消息，曹操出行今日宣布与豆包联合打造 AI 打车服务 ，首批在北京、杭州、苏州三城上线，这意味着曹操出行将出行服务能力与 AI Agent 深度融合。 AI 打车服务上线后，当用户在豆包产品端咨询路线、地点、休闲娱乐…

Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and …

Large Language Models demonstrate remarkable proficiency in static reasoning, yet training them as autonomous agents thr…

Model misalignment, prompt injection, or operator misuse could lead AI agents operating frontier-lab accounts to exfiltr…

Designing and authoring high-performance custom kernels for accelerators is a complex task that requires deep hardware-l…

Vision-language-action (VLA) models map visual observations and language instructions directly to robot actions, but lon…

Anthropic 发布模型上下文协议（Model Context Protocol），以开放标准统一 LLM 应用与外部数据源、工具的连接方式，被社区称为'AI 应用的 USB-C 接口'。

Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. M…

Visual generation is evolving from generative models used through a single invocation into agentic control processes tha…

Diverse and simulation-ready indoor scenes are essential for interactive entertainment and embodied AI, yet their scalab…

We present a continuous, population-scale measurement record of autonomous language-model trading agents operating in pr…

Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of …

Anthropic 随 Claude 3.7 Sonnet 推出命令行编程智能体 Claude Code，可自主读写代码库、运行测试与提交修改，开启'终端 Agent'产品形态。

Large language models (LLMs) are increasingly used to formulate optimization models from natural-language problem descri…

Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, y…

Peter Steinberger 的开源个人智能助理项目（前身 ClawdBot / MoltBot）更名为 OpenClaw 并刷屏科技圈，7×24 小时待命的'电子员工'形态引发全网部署热潮。

Google 在 I/O 大会全面转向 AI First：Gemini 2.5 Pro/Flash 系列落地百亿级用户产品，AI Mode 重构搜索交互，Veo/Imagen 视频图像生成商用化。