Topic · 主题全部主题 →

Agent 智能体

让模型自主规划、调用工具、完成多步任务的技术方向——从 Claude Code、Manus 到各家 Agent 框架与评测基准的全部动态。

9,105条收录
1,107条精选

精选归档 · 第 47 页

921940 条 · 共 1,107

4月2日

星期四 · 2 条
00:00
智谱:研究(网页内嵌数据)精选
GLM-5V-Turbo发布:多模态Coding基座模型

智谱发布GLM-5V-Turbo多模态Coding基座模型,原生支持图像、视频、设计稿理解及画框、截图、读网页等工具调用,上下文窗口达200k。采用新一代CogViT视觉编码器与30+任务协同强化学习,在保持纯文本编程能力的同时强化GUI Agent能力。与Claude Code、AutoClaw等框架深度协同,支持"图像即代码"前端复刻及GUI自主探索,提供开箱即用的官方Skills。


推荐理由:智谱发布多模态Coding基座GLM-5V-Turbo,深度适配Claude Code等Agent
00:00
Claude:Blog(网页)精选
构建 Claude 应用的三大最佳实践

Anthropic 分享构建 Claude 应用的三大实践:使用 Claude 已掌握的通用工具(如 bash 和文本编辑器);允许其自行编排工具调用链,减少不必要的上下文回传以降低 token 消耗;随着模型能力进化,重新评估 agent harness 的预设限制。实测显示,让 Opus 4.6 自主过滤工具输出,在 BrowseComp 基准测试中准确率从 45.3% 提升至 61.6%。


推荐理由:Anthropic官方分享构建Claude Agent的三大最佳实践,含模型性能数据与代码编排技巧

4月1日

星期三 · 3 条
23:03
Jim Fan@DrJimFan精选
CaP-X开源发布:大模型智能体进入物理世界The power of the Claw, in the palm of a robot hand. Agentic robotics is here! Today, we open-source CaP-X: vibe agents, alive in the physical world. They incarnate as robot arms and humanoids with a rich set of perception APIs, actuation APIs, and auto synthesize skill libraries as they go. CaP-X is a strict superset of our old stack, because policies like VLAs are “just” API calls as well. It solves many tasks zero-shot that a learned policy would struggle with.And we are doing much more than vibing. CaP-X is our most systematic, scientific study on agentic robotics so far:• We build a comprehensive agentic toolkit: perception (SAM3 segmentation, Molmo pointing, depth, point cloud), control (IK solvers, grasp planner, navigation), and visualization (EEF, mask overlays) that work across different robots. • CaP-Gym: LLM’s first Physical Exam! 187 manipulation tasks across RoboSuite, LIBERO-PRO, and BEHAVIOR. Tabletop, bimanual, mobile manipulation. Sim and real. Can’t wait to see the gradients flow from CaP-Gym to the next wave of frontier LLM releases. • CaP-Bench: we benchmark 12 frontier LLMs/VLMs (Gemini, GPT, Opus, Qwen, DeepSeek, Kimi, and more) across 8 evaluation tiers. We systematically vary API abstraction level, agentic harness, and visual grounding methods. Lots of insights in our paper. • CaP-Agent0: a training-free agentic harness that matches or exceeds human expert code on 4 out of 7 tasks without task-specific tuning. • CaP-RL: if you get a gym, you get RL ;). A 7B OSS model jumps from 20% to 72% success after only 50 training iterations. The synthesized programs transfer to real robots with minimal sim-to-real gap.3 years ago, our team created Voyager, one of the earliest agentic AI that plays and learns in Minecraft continuously. Its key ideas — skill libraries, self-reflection loops, and in-context planning — have since influenced many modern agentic designs.Today, the agent graduates from Minecraft and gets a real job. It’s April Fool’s, but this Claw is getting its hands dirty for real!Link in thread:CaP-X开源具身智能系统,让大模型智能体通过机械臂与人形机器人进入物理世界。系统整合SAM3、Molmo等感知API与IK求解器、抓取规划等控制接口,可自动合成技能库。研究发布CaP-Gym基准(187项操作任务)与CaP-Bench(评测12个前沿模型),提出零样本框架CaP-Agent0及强化学习方案CaP-RL,后者仅用50次迭代即将7B模型成功率从20%提升至72%。该技术由曾开发Minecraft智能体Voyager的团队推出。

推荐理由:NVIDIA Jim Fan 开源 CaP-X,让 Vibe Agent 真正进入物理世界操作机器人
08:00
Google Developers Blog(RSS)精选
AI 评分 71/100
开发者指南:使用技能构建ADK智能体

Agent Development Kit (ADK) SkillToolset 推出了“渐进式披露”架构,使AI智能体能够按需加载领域专业知识,与传统单体提示相比,可减少高达90%的令牌使用量。该系统通过四种模式——从简单的内联清单到智能体可自行编写代码的“技能工厂”——使智能体能在运行时利用通用的 agentskills.io 规范动态扩展其能力。这种模块化方法确保了复杂的指令和外部资源仅在相关时被访问,从而为现代AI开发构建了一个可扩展且能自我扩展的框架。


推荐理由:开发者可借鉴此架构,构建更智能、更经济的AI代理。
06:34
Ethan Mollick:One Useful Thing(RSS)精选
Claude Dispatch 与界面的力量

AI 能力已足够强大,但人们仍缺乏趁手的工具和界面来完成实际工作。Claude Dispatch 强调,优秀的界面设计才是释放 AI 全部潜力的关键。


推荐理由:Ethan Mollick 深度解析 Claude 与 AI 界面力量,洞察工具与能力的鸿沟

3月31日

星期二 · 3 条
21:00
OpenAI:官网动态(RSS · 排除企业/客户案例)精选
加速 AI 下一阶段发展

OpenAI 获 1220 亿美元新融资,用于全球扩展前沿 AI、投资下一代算力,满足 ChatGPT、Codex 及企业 AI 的需求增长。


推荐理由:OpenAI获1220亿美元巨额融资,创AI行业融资纪录
16:37
Artificial Analysis@ArtificialAnlys精选
KwaiKAT发布KAT-Coder-Pro V2:非推理代码模型性能比肩Claude Sonnet 4.6KwaiKAT has released KAT-Coder-Pro V2, a non-reasoning model that scores 44 on the Artificial Analysis Intelligence Index, an 8 point improvement from KAT-Coder-Pro V1@KwaiAICoder has updated their flagship proprietary coding model with the release of KAT-Coder-Pro V2. KAT-Coder-Pro V2 achieves 44 on the Artificial Analysis Intelligence Index, matching Claude Sonnet 4.6 (non-reasoning) and trailing only Claude Opus 4.6 (non-reasoning, 46) among non-reasoning models. At ~9M output tokens, it is also more token efficient than Claude Opus 4.6 (~11M), Claude Sonnet 4.6 (~14M), and reasoning models with similar intelligence such as DeepSeek V3.2 (reasoning, ~61M) and Qwen3.5 397B A17B (reasoning, ~86M).KAT-Coder-Pro V2 is a non-reasoning model, unlike all of the current frontier language models which ‘think’ before answering. Typically, reasoning variants score higher on the Intelligence Index than their non-reasoning counterparts, but consume more output tokens and are less suited to latency-sensitive workloads.Key Highlights:➤ 🧠 Higher overall intelligence, but regression in long context reasoning and knowledge recall: KAT-Coder-Pro V2 scores 44 on the Artificial Analysis Intelligence Index, an 8 point improvement from KAT-Coder-Pro V1 and matching Claude Sonnet 4.6 (non-reasoning, max effort). It performs well on tool use (90% on Tau2-Telecom), but regresses compared to KAT-Coder-Pro V1 on long-context reasoning and knowledge, falling 8 p.p. on AA-LCR (66%) and 17 p.p. on HLE (16%).➤ 🤖 Agentic capability improvements: KAT-Coder-Pro V2 shows major improvements on our agentic evaluations. On Terminal-Bench Hard, it scores 49%, up 40 p.p. from KAT-Coder-Pro V1, making it the highest-scoring non-reasoning model, matching Claude Opus 4.6 (non-reasoning, 49%) and ahead of Claude Sonnet 4.6 (non-reasoning, 46%). KAT-Coder-Pro V2 also shows improvement in GDPval-AA, scoring 1123 (+304 Elo from V1), but still sits behind models such as DeepSeek V3.2 (1198) and Qwen3.5 397B A17B (1202).➤ ⚙️ High token efficiency: KAT-Coder-Pro V2 is a non-reasoning model and uses fewer tokens than peers with similar intelligence. It uses 8.7M output tokens to run the Artificial Analysis Intelligence Index, below Claude Opus 4.6 (non-reasoning, ~11M) and Claude Sonnet 4.6 (non-reasoning, ~14M), though this is ~2x higher than its predecessor, KAT-Coder-Pro V1 (~4.5M). It also uses significantly fewer tokens than similarly intelligent reasoning models such as DeepSeek V3.2 (reasoning, ~61M) and Qwen3.5 397B A17B (reasoning, ~86M).➤ $ Improved cost efficiency: KAT-Coder-Pro V2 costs $73 to run the Artificial Analysis Intelligence Index, down from $76 for V1, as it uses fewer input tokens by requiring fewer turns in agentic evaluations. This makes it one of the most cost-efficient models at its intelligence level, costing less than Qwen3.5 397B A17B (reasoning, $418) and Claude Sonnet 4.6 (non-reasoning, $1397). KAT-Coder-Pro V2 is currently priced at $0.30/$1.20 per 1M input/output tokens on StreamLake and AtlasCloud API endpoints.➤ ⚡ Low end-to-end response time: KAT-Coder-Pro V2 runs at ~109 output tokens per second, far ahead of Claude Opus 4.6 (non-reasoning, 39 OTPS) and Claude Sonnet 4.6 (non-reasoning, 43 OTPS). Because it also has a low time to first token without any reasoning delay, it delivers one of the fastest end-to-end response times, which measures the time taken from request sent to final output returned.Model details:➤ Availability: KAT-Coder-Pro V2 is available via StreamLake and AtlasCloud API endpoints ➤ Context Window: 256K tokens (equivalent to KAT-Coder-Pro V1) ➤ Multi-modal capabilities: Text input and output onlyKwaiKAT发布非推理代码模型KAT-Coder-Pro V2,在Artificial Analysis Intelligence Index获44分,较V1提升8分,与Claude Sonnet 4.6持平。该模型token效率显著,运行仅需约9M输出token,远低于Claude系列及DeepSeek等推理模型。Agent能力大幅提升,Terminal-Bench Hard得分49%(提升40个百分点),匹配Claude Opus 4.6。成本降至73美元,响应速度达109 token/秒。但在长上下文推理和知识回忆方面较V1有所退步。

推荐理由:快手发布 KAT-Coder-Pro V2,非推理架构实现 44 分智能指数,Agent 能力跃升 40 个百分点,成本仅为 Claude Sonnet 的 5%。
08:00
Google Developers Blog(RSS)精选
AI 评分 81/100
ADK Go 1.0 正式发布:迈向生产就绪的多智能体开发框架

Agent Development Kit (ADK) for Go 1.0 版本正式发布,标志着其从实验性脚本转向生产就绪的服务框架。本次更新核心在于强化可观测性、安全性与可扩展性,主要特性包括:原生集成OpenTelemetry以实现深度追踪;支持自愈逻辑的新插件系统;在敏感操作中引入“人在回路”安全确认机制。此外,新版本提供了基于YAML的配置以加速迭代,并优化了Agent2Agent协议,以支持跨编程语言的智能体无缝通信。该框架使开发者能够依托Go语言的高性能工程标准,构建复杂且可靠的多智能体系统。


推荐理由:Go 语言开发者迎来官方 AI Agent 开发框架,可快速构建可靠多智能体系统。

3月30日

星期一 · 3 条
08:00
Google Developers Blog(RSS)精选
AI 评分 81/100
Google 发布 Java 智能体开发套件 (ADK) 1.0.0 版本

Google 正式发布了 Java 版智能体开发套件 (ADK) 的 1.0.0 版本。该版本引入了多项关键功能:支持接入 Google Maps 数据、内置 URL 抓取工具,以及用于跨框架协作的标准化 Agent2Agent 协议。其全新的“App”和“Plugin”架构增强了控制能力,实现了全局日志记录、通过事件压缩自动管理上下文窗口,以及需要人工确认的“Human-in-the-Loop”工作流。此外,该版本深度集成 Google Cloud 服务(如 Firestore 和 Vertex AI),提供了强大的会话与记忆管理功能,以处理长期状态和大型数据工件,助力开发者构建更复杂的 AI 智能体应用。


推荐理由:Java开发者可利用官方工具快速构建集成Google服务的AI代理。
04:00
Qwen:Blog Retrieval(API)精选
Qwen3.5-Omni:全面扩展,迈向原生全模态 AGI

Qwen Studio 发布,集成聊天机器人、图像视频理解、图像生成、文档处理、网页搜索、工具使用及 Artifacts 功能,提供全模态 AI 一站式解决方案。

另有 1 家信源报道Qwen:Blog Retrieval(API)
推荐理由:阿里发布Qwen3.5-Omni多模态模型,迈向原生全模态AGI

3月28日

星期六 · 3 条
11:25
Greg Brockman@gdb精选
Codex use cases:面向人类的 SkillsCodex use cases are like Skills, but for humansOpenAI 推出 Codex use cases 示例库,涵盖编程与非编程任务的实用场景。用户可在 Codex 应用中直接打开各用例的 starter prompt 开始使用。

Romain Huet: We just launched Codex use cases! It’s a gallery of practical examples across coding and non-coding tasks, with real way...


推荐理由:OpenAI Codex 推出使用案例库,覆盖编程与日常任务,可直接在应用中试用。

3月27日

星期五 · 6 条
20:00
Cursor Blog精选
AI 评分 72/100
Composer 2技术报告:面向智能体软件工程的代码模型训练

本报告介绍了代码模型Composer 2的训练过程。该模型基于开源基础模型Kimi K2.5,通过两阶段训练:首先进行侧重代码的持续预训练以深化编码知识,随后在高度模拟真实Cursor环境的大规模强化学习中提升端到端智能体性能。在自建的真实任务评估集CursorBench上,Composer 2得分为61.3,较前代提升37%,与前沿模型性能相当。在公开基准SWE-bench Multilingual和Terminal-Bench上分别获得73.7和61.7分,并在保持高精度的同时实现了显著更低的推理成本。训练依托为Blackwell GPU定制的高效MoE训练内核、跨区域异步强化学习管道等大规模基础设施完成。


推荐理由:Cursor 把 Composer 2 的训练全流程摊开讲了,从 Kimi K2.5 继续预训练到大规模 RL,关键是 RL 在真实 Cursor 会话里跑,不是玩具环境。做 coding agent 的团队,这份报告值得逐段拆。
10:20
09:56
Greg Brockman@gdb精选
Codex 正式上线 Plugins 功能Plugins are now available in Codex:Codex 正式上线 Plugins 功能,开箱即用支持 Slack、Figma、Notion、Gmail 等主流开发工具,开发者可直接在 Codex 中调用这些服务。

OpenAI Developers: We're rolling out plugins in Codex. Codex now works seamlessly out of the box with the most important tools builders alr...


推荐理由:OpenAI Codex 正式上线插件系统,开箱即用地连接 Slack、Figma 等主流工具
00:10
Andrej Karpathy@karpathy精选
Stripe Projects:让 AI 自动完成 DevOps 全流程When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make it real, the DevOps: services, payments, auth, database, security, domain names, etc...I am really looking forward to a day where I could simply tell my agent: "build menugen" (referencing the post) and it would just work. The whole thing up to the deployed web page. The agent would have to browse a number of services, read the docs, get all the api keys, make everything work, debug it in dev, and deploy to prod. This is the actually hard part, not the code itself. Or rather, the better way to think about it is that the entire DevOps lifecycle has to become code, in addition to the necessary sensors/actuators of the CLIs/APIs with agent-native ergonomics. And there should be no need to visit web pages, click buttons, or anything like that for the human.It's easy to state, it's now just barely technically possible and expected to work maybe, but it definitely requires from-scratch re-design, work and thought. Very exciting direction!构建现代应用的最大挑战并非代码本身,而是 DevOps 中繁琐的服务集成、API 密钥管理和部署配置。作者期待未来 AI 智能体能自动完成从文档阅读到生产环境部署的全流程,无需人工点击网页或手动配置。Stripe 推出的 Projects 正是朝此方向迈进:开发者可通过 CLI 命令自动配置 PostHog 等第三方服务,实现账户创建、密钥获取和计费设置的自动化,真正将基础设施生命周期转化为代码。

Patrick Collison: When @karpathy built MenuGen (https://karpathy.bearblog.dev/vibe-coding-menugen/), he said: "Vibe coding menugen was exh...


推荐理由:Karpathy指出Vibe Coding最大痛点是DevOps集成,Stripe Projects让Agent直接CLI配置服务免人工点击