Agent usage is shifting toward long-horizon tasks such as coding and scientific discovery, among which terminal tasks ar…

Coding 之后，教育 Agent 正在成为下一场 Token 战争 #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。 ]

Multi-Agent Reinforcement Learning (MARL) has emerged as a pivotal paradigm for complex decision-making in autonomous sy…

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。

Large language model (LLM)-based multi-agent systems (MAS) achieve strong performance by employing specialized multiple …

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。

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

系统拆解吴恩达 2026 年 8–9 月连发五封来信构建的《AI 工程技能地图》：四大顶层能力、编程智能体的三阶段工作流与五项细分技能，剖析其数据方法论、隐藏主线与三条反主流论断，并对地图本身的边界与争议做批判性审视，附个人自评与团队落地清单。

AI 没有消灭交付瓶颈，只是把瓶颈从"写代码"搬到了"验证代码"。本文基于 2 篇 arXiv 论文、DORA 2025 报告与 2026 年三份行业基准（LinearB 8.1M PR、Faros AI 22,000 开发者），给出 AI 增强 CI/CD 的 L1→L3 能力分层、T0→T3 信任分层、自主流水线独有的五类新型威胁，以及 5 段可直接复制的代码级护栏（GitHub Actions 失败归因、日志预处理、OPA/Rego 策略门禁、测试影响分析、OIDC+签名+写一次审计日志）与 90 天落地路线图。关键数据：任务吞吐 +33.7% 但评审耗时 +441.5%、生产事故/PR 比值 +242.7%；AI PR 30 天合并率 32.7% vs 人工 84.4%；论文实验中 Lead Time −35%、CFR −38%、MTTR −43%，AI 干预准确率 87.5%、人工否决率 14.3%、零策略违规。

IT之家 9 月 10 日消息，智谱今天（10 日）通过 Bigmodel 开放平台宣布启动“智谱 · 杭州全城 Coding 计划”，该计划是智谱联合杭州市、上城区推出的城市级 AI 编程普惠行动，全国首创城区级 AI 模型调用支持。 该…

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

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。

看清「一个真正的人」]

Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence i…

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。

面向工程师的 OpenClaw 架构深度长文：四层设计总览、Gateway 单进程控制平面、Agent Loop 完整生命周期、Markdown 记忆管线、四槽插件体系、安全模型与多代理路由，还原一个生产级 AI Agent 运行时的设计取舍。

Agents can turn shared infrastructure into a channel for coordinated intrusion. The HF Mirror incident and a separate pu…

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

把 2026 年可核查的公开证据整理成一张六层能力路线图——预训练、后训练 RL、推理时计算、上下文与记忆、智能体与 Harness、世界模型。含 Meta ScaleRL 40 万 GPU 小时实验结论、RL 预算占比 10%–30% 口径、Chinchilla 对比、Meta-Harness 6x 差距等数据锚点，并给出优先级表与算法工程师/产品经理的行动建议。

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

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。

Android/Kotlin 生态基石人物 Jake Wharton（Retrofit、OkHttp 作者，Google Kotlin 团队第一位工程师）在 KotlinConf'26 访谈中公开表态：找工作的第一条标准就是"不碰 AI"，直接排除约 80% 的雇主，且至今从未用 AI Agent 写过代码。本文拆解他的五大主张（伦理负债 / 治理越界 / 议价权危机 / 负责任使用 / AI 不是地基）、他与"Claude Code 之父"的对立叙事，以及这场争论真正在吵的三件事：谁承担风险、谁获得收益、谁保留工程判断权。

1 万个 AI Agent，挑战百年数学难题 #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。 ]

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 …

Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a …

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

We study scheming in LLM agents, in which agents covertly pursue misaligned goals. Our focus is to understand how schemi…

Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used t…

SWE-Bench Pro has emerged as a standard benchmark for evaluating software engineering agents on challenging repository-l…

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

Sequential memory agents process long documents by reading chunks one after another while maintaining a compact memory s…

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…

Automating empirical research is a long-standing direction of AI. Recent automatic research (AutoResearch) agents bring …

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。

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'。

IT之家 9 月 11 日消息，OpenAI 于当地时间 9 月 10 日宣布推出 Agents API 公测版，允许开发者通过 API 调用由 OpenAI 管理的云端 AI 智能体运行环境。 该服务复用了 Codex 背后的智能体执行框…

把"模型发布"当成一类可度量的事件冲击来研究。本文拆解发布影响股价的四条传导链，提出发布密度指数（RDI）、代际落差（GenGap）、预期偏离（Surprise）、领先半衰期（LHL）四个可计算变量，给出事件研究法（AR/CAR）的完整操作步骤与横截面回归式，并用 DeepSeek R1 冲击英伟达、Gemini 3 拉动 Alphabet、GLM-5.2 把智谱送上万亿、Kimi K3 两日击落智谱 42%、GLM-5.3"更强却更跌"、GPT-6 Astra 引发"硬件跌停应用涨停"等 7 个正反面样本做复盘。

A research idea may be novel, coherent, and scientifically plausible, yet its proposed method may remain insufficiently …

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

While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autono…

AI research agents combine prior knowledge, public sources, and experimental feedback to produce useful results. The Dis…

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

High-quality structured organic reaction data are essential for developing artificial intelligence for chemistry (AI4Che…

Large Language Model (LLM) agents are turning language into real-world effects, making safety necessary against both ind…

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