从「补全一行代码」到「自主跑完一个任务」，AI 编程工具这两年完成了形态跃迁。本文拆解 Agentic Coding 的核心——感知-行动循环、工具集、权限模型与上下文管理，讲清它与补全式 Copilot 的本质区别，以及从 Claude Code 到 Cursor 的路线分野。

JetBrains InnovationHub 开源的智能体 IDE：以进程内 pi 编码智能体为引擎，每个任务一条 git worktree 与分支实现并行隔离，用代码旁可被 Agent 读写的 SPEC.md 图谱承载项目意图，并用版本化类型协议把前端与宿主解耦。本文拆解其 spec_* 工具读模型、WsErrorCode 封闭集与 MCP 按调用授权，并如实标注 0.x 无基准、规格自我指涉风险与「越用越好用」的营销边界。

Google 比 OpenAI 早七周发布 Deep Research，但把「研究计划让用户改批」产品化的也是它——agentic 检索的通用循环是：规划、迭代检索、阅读、反思补漏、交叉验证、带引用报告。本文拆解这个循环的两种实现路线（端到端 RL vs 显式编排），用 BrowseComp 上「裸模型不足 10% vs deep research 51.5%」的差距说明多步浏览行为本身值多少分，也把「慢不等于对」的引用可靠性研究摆上台面。

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。

LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural…

We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activat…

At a glance Harnessed Agentic RL: Microsoft Research Asia introduces a training paradigm in which the same agent harness…

We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with…

Agentic reinforcement learning (RL) disaggregates training from rollout, so each policy update must reach the rollout cl…

At OpenAI’s DevDay event on Tuesday, the company announced the launch of Dots, a new personal agentic assistant powered …

Google Research has introduced an **AI video co-director** for long-form video generation. The suite of 4 agentic framew…

OpenAI announced on Wednesday that it is bringing voice-based agentic features to mobile, allowing users to trigger work…

Compositional 3D scene reconstruction has recently been explored from two directions: agentic reasoning that provides se…

Agentic memory is becoming essential for long-horizon AI agents, yet many existing systems rely on autoregressive LLMs t…

Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many inte…

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

2026 年 10 月 17 日，DeepSeek 一条官方新闻让「许愿式编程」刷屏中文技术圈，但这个术语的身世远比一次发布复杂：它脱胎于 1985 年 SICP 的教学黑话，在 2025 年被 Andrej Karpathy 的 vibe coding 重新点燃，又花了大半年从贬义词变成官方卖点。本文按时间线拆解术语谱系，辨析它与 vibe coding、agentic engineering、规格驱动开发的分野，并用 METR、DORA、Stack Overflow 的数据与 Replit 删库等事故，回答「许愿」何时是真生产力、何时是灾难。

从控制流与上下文的所有权出发，给出四条可执行的 Agent 工程原则：一切外部接入以工具体系形式接入且不注入系统提示词；逐级披露贯穿技能、工具发现、工具执行与记忆四个环节；Workflow / Agent / Agentic Workflow / Graph 各有场景、不是替代关系；并逐层拆解四者的技术原理——DAG 与状态机、ReAct 循环、宏观图加微观循环的混合架构，以及 State/Node/Edge、超步执行、reducer 合并语义、checkpointer 恢复、interrupt 人审与递归上限。

!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…

!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…

!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…

Vision-language models (VLMs) can perform a broad range of tasks across diverse settings, yet their performance in agent…

Complex camera motion is central to visual storytelling, yet translating cinematographic intent into controllable, execu…

Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensiv…

Reconstructing complete, scene-aligned 3D objects from casual images requires integrating sparse, uncertain observations…

Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution sh…

!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…

Building on nearly a decade of co-engineering, CoreWeave has built NVIDIA compute, networking and software into a cloud …

LLM agents generate intermediate reasoning and actions token by token, making extended interactions slow and computation…

Foundation models can serve as clinical agents through tool-use harnesses. However, conventional medical benchmarks asse…

Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specified…

Last week, TypeSafe AI released Jev, its first **System One model**. Founder Diogo Almeida previously worked at OpenAI o…

Large language models (LLMs) excel at structured, verifiable tasks, but their low-entropy bias can produce homogeneous a…

Reinforcement learning (RL) for code agents often uses executable tests to provide binary rewards. With these rewards, G…

Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed ou…

To build and deploy sophisticated robotics applications that can perceive, reason and act in dynamic environments, devel…

拆解 GitHub 14.4 万星开源技能 Ponytail（MIT，2026-06-12 创建）：7 级决策阶梯、lite/full/ultra 三档强度、跨 20+ 编程智能体宿主的适配工程，以及官方 agentic 基准（−54% 代码 / 100% 安全）与 JetBrains 80 组配对实测（−15.4% 代码 / −10.3% 成本，p=0.004）的三次基准对撞；附设计系统、小模型、指令层三大边界与 6 条落地清单。

StepFun has released Step 5 Preview, a sparse Mixture-of-Experts model with 600B total parameters and 27B active per tok…

Alibaba's Qwen3.8-Omni-Flash understands audio and video, plans tasks, calls tools, and reports about 45.7% fewer tokens…

Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-sour…

Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivate…

Multimodal agents can create complex videos in software such as Blender by coding without relying on diffusion models. Y…

Video diffusion models are stochastic and hard to control: precise content often requires repeated sampling without guar…

As AI agents become participants in the development of their successors, they reshape both the production of intelligenc…

In this work, we present ZGCM-1, a fully open 7B dense foundation model trained from scratch with extreme data, system, …

三种概念的系统辨析：预定义代码路径 vs 运行时策略驱动，附选型决策框架与混合架构实践

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

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

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

“We’re at an inflection point in cybersecurity,” Jensen Huang told a sold-out crowd at CrowdStrike’s Fal.Con 2026 in Las…