Moonshot AI Releases Kimi K3.1 Pro: A 2.8T Total/104B Active Params (MoE) Model with 1M Context !(https://www.gstatic.co…

一周涨星 2,968 的编码智能体上下文网关：沙箱执行只回流 stdout、SQLite FTS5 零 LLM 检索、压缩快照防失忆，官方基准整会话 315 KB→5.4 KB。本文并排展示第三方保留意见——98% 未经独立复现、有损摘要会破坏指纹契约，以及它真正暴露的 17 平台 hook 能力差异。

Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may no…

Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, fr…

Perplexity Research and turbopuffer have released **pplx-embed-v2-context-9b-preview**, a contextual embedding model for…

While Large Language Models (LLMs) advertise million-token context windows, reasoning quality often collapses as inputs …

Training a Mixture-of-Experts (MoE) model at long context or large batch size fails as soon as any one component's peak …

Recently, linear attention layers have been increasingly adopted to replace softmax attention at scale for long-context …

Few-shot in-context learning (ICL), the capacity of a model to infer abstract patterns from input-output examples provid…

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

Sponsored In partnership withCelonis Enterprise AI can generate recommendations, automate tasks, and help organizations …

!(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…

Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference e…

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…

Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No fini…

Scaling large language models efficiently has motivated sparse capacity mechanisms such as Mixture-of-Experts and, more …

Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by sel…

Speculative decoding accelerates rollout generation, which dominates the cost of reinforcement learning (RL) post-traini…

Text-driven 3D generation has advanced rapidly in creating large-scale outdoor environments and detailed indoor scenes, …

发布不到两年，MCP 从 Anthropic 的一个开放标准长成了 AI 应用连接层的事实标准——又在 2026-07-28 的规范里把自己重构了一遍：会话没了、握手没了、sampling 和 roots 被废弃。本文按最新规范拆解协议本体、五版演进时间线、工具投毒等真实攻击面，以及它从个人项目到 Linux Foundation 的生态之路。

《Language Models are Few-Shot Learners》（Brown et al., 2020）把 GPT-3 推到 175B 参数，真正的发现却是另一个：只靠提示词里放几个例子，模型就能完成没训过的任务——in-context learning 从此改写了 NLP 的工作方式。本文精读这篇论文的机制、数据与遗留争议。

Linear attention enables efficient long-context autoregressive decoding by compressing history into recurrent states, bu…

Agent 工程系统学习第 5 章：工具是 Agent 的手脚。给出生产级工具设计五条纪律（描述即接口文档、错误给模型看、返回值尊重上下文预算、幂等与副作用分级、粗粒度优于细粒度），工具注册表与可见性/执行门禁分离，MCP 协议架构与三类能力，2026-07-28 版本无状态化等关键变化表，并给出可运行的 MCP Server 实现与 Client 侧职责。

Language model agents are deployed with a harness, the software around the model that manages its context, tools, and fe…

Long-context LLM agents accumulate interaction histories that strain KV-cache memory and attention computation. Although…

Streaming world models should render a place consistently across repeated visits. Directly supervising such revisits req…

An assistant that serves the same user over a long horizon has to answer from what that user has revealed: which prefere…

Pretrained transformers use little of their depth to follow references in context. Thirteen base models reliably follow …

Coding agents now run for hours, not minutes. Every edit, test run and log read goes back into the model’s context. A te…

系列第 ③ 篇，对应技能地图第 2 格「Grounding」。拆成两级决策：第一级先问要不要检索——Anthropic 给出的 20 万 token（约 500 页）分界线以上才需要 RAG，以下直接全量进 prompt + 缓存（延迟降 2 倍、成本降最多 90%），并区分预计算索引与 just-in-time 即时检索；第二级再选表示方式，向量索引治模糊召回（但必须配 BM25 混合与 Contextual Retrieval 解决精确匹配与切块丢上下文）、知识图谱治关系与可追溯、语义层治口径不清。附可量化收益表（检索失败率 5.7% → 3.7% → 2.9% → 1.9%）、四个实现注意项、context rot 与上下文压缩/笔记/子智能体三件套，以及一张可抄的选型决策树。

Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity obser…

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

Linear attention is increasingly used in frontier language models for efficient long-context inference and constant-memo…

Can one language model hand its live memory to another without the receiver rereading the context? We demonstrate useful…

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

Many NLP tasks, such as summarization and extractive question answering, reduce to retrieving relevant content from docu…

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'。

一次 RAG 请求到底花多少钱？查询向量化几乎免费，检索只要几厘，生成环节却吃掉九成账单。本文把成本拆成一次性入库与每次请求两栏，给出各环节的量级估算方法与七个省钱杠杆，以及一条先砍生成、再调检索的平衡框架，帮你把预算花在真正影响账单的地方。

窗口从 8K 涨到千万级，「RAG 已死」论再起。但评测数据显示有效上下文远小于宣称窗口，长输入的成本与延迟也要另算一笔账。本文用论文与定价证据拆解两者分工：小库精读交给长窗口，大库「找得到、读得起」仍靠检索。

obra/superpowers 单日再涨 1,096 星。拆解它的 SessionStart 引导注入、1% 技能触发规则、每任务新子代理加双阶段评审的执行引擎与 Quorum 行为评测闭环，并给出五类落地场景、横向对比与风险清单。

港大数据智能实验室出品，上线十个月拿下四万五千星：一条单循环 agent 流水线跑全部十种学习模式，L1/L2/L3 三层记忆全部落盘可审计，九种 RAG 引擎可评测可切换，自带十五路 IM 渠道与 EduHub 技能市场。

290,802 星的 agent harness 操作系统 2.2.3 线新增面拆解：GateGuard 在首次编辑前拒绝并要求交出具体事实（官方 A/B +2.25 分、代价约 45% 轮次），四档 harness 保真度矩阵自陈「不支持」，Memory Vault 三作用域只创建、unreviewed、拒密钥、不跟符号链接。并如实并排展示它自己公布的 72 场试点「只测到成本、没测到效果」。

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。

WHO、AAP 与中国国家卫健委的口径高度一致：越早越少、越少越好、共看优先。屏幕的主要问题不是「辐射」，而是挤占互动、游戏与睡眠，以及低龄儿童特有的「视频缺陷」。本文拆解三套指南的时间表、四条机制证据与常见误区，给一份可执行的家用媒体公约。

!(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…

UCLA/MIT 背景团队开源的多智能体投研框架：四个分析师并行取证、多空研究员结构化辩论、三档风控独立审议、组合经理五档评级拍板，并用已实现收益结算决策记忆。本文拆解其状态机与评级解析机制、五类落地场景，并如实标注论文仅三个月窗口、夏普比率超经验范围等边界。