2026-10-22 AI 日报

OpenShell is the safe, private runtime for autonomous AI agents.

一个基于 DeepSeek Harness 插件机制构建的多端远程访问方案，通过安全、低延迟、端到端加密的 P2P 优先网络，支持从 PC、Android 和 Web 随时访问并操作远程 Harness 和 CodeX。 (A multi-device remote access solution built on…

The best DeepSeek Harness plugin for context insight and management, with context dashboard / browser / sidebar and context command, for context statistics,…

A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.

TradingAgents: Multi-Agents LLM Financial Trading Framework

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and…

Orca is the place for working with a fleet of agents (e.g. Grok Bot, Claude Code). Run any coding agent with your own subscription. Available on desktop,…

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image…

A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or…

As streaming video generation advances, enabling real-time interaction with generated video is becoming increasingly important. We introduce StreamEval, a…

Autoregressive video diffusion models generate videos chunk by chunk, yet producing plausible continuations does not guarantee that they capture how scenes…

Despite recent progress in dexterous reference tracking, existing models focus primarily on single-hand manipulation and a limited range of interactions,…

Large Language Model (LLM) agents can handle increasingly complex tasks, navigating long trajectories of observations and actions. As these trajectories grow,…

Post-hoc image explanations usually show where a model looks using spatial heatmaps or indicate which channels matter using global channel scores. These…

Spatial intelligence requires agents to actively acquire visual evidence and integrate observations into a coherent representation of the three-dimensional…

Scaling data, diversity and model capacity has improved embodied learning in physical environments, where diverse experiences remain grounded in shared…

Agent learning is shifting from learning from human data toward learning through interaction with the world. However, scaling such learning directly in…

A login screen that appears after a tap on Sign in is expected; the same screen after a tap on View order is an attack. For GUI agents, safety is therefore a…

Multimodal code intelligence connects the symbolic world of programs with the visual world their execution creates. Interest in this capability is burgeoning,…

Keane Lucas, Aengus Lynch, Luna Tong, Luke Champine, Zygi Straznickas, Dino Distefano, Harshikaa Agrawal Evyatar Ben Asher, Ava Howell, Sami Jawhar, Chris…

Title is a bit of an exaggeration but the question is more: if the frontier models are so good, why even sell them as your primary money maker? Couldn't…

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that…

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that…

https://t.co/Ev0g2EbAyw

Introducing Canva Craft 🚀 Extraordinary image generation is now available to everyone, powered by our first frontier model built specifically for design.…

Carbon-X is a 14.8B parameter decoder-only model that takes raw DNA in a normal chat and answers in English. It shares one token stream for text and DNA,…

Introducing Ling-3.1-flash-1019 🚀 It scores 44 on the Artificial Analysis Intelligence Index, up from 41 for Ling-3.1-flash. Gains in agentic work:…

I've been building capy-flash, an open-source inference engine for running Qwen3.8-Flash-Next (125B MoE) and Qwen3.8-27B on consumer RTX 50 cards. Until now…

An edit LoRA for MOSS Image has been released. Works with both Base and SFT. Weights: https://huggingface.co/chinoll/Moss-Image-Edit Custom nodes / Workflows:…

Kimi K3.1 vs Qwen 4: 3D helicopter Same prompt, takeoff/land, 3D assembly and exploded views, very similar gen time at around 15-20 minutes for both China are…

New Features Save reusable prompts and slash commands in ten numbered /presets slots, with a keyboard menu for quick access. (#54380, #54381) Set model,…

The Decisions API is now generally available with gpt-6-luna. Cache shared input across requests for prompt-cache discounts, include images in individual…

Z.ai GLM 5.3 Flash (zai-glm-5-3-flash) is now available. A multimodal 320B-parameter (18B active) Mixture-of-Experts model from Z.ai with a 1M-token context…

API Gateway now supports real-time streaming—including Server-Sent Events, WebSockets, gRPC, and chunked transfer encoding—in Public Preview without requiring…

Fast, focused, low-cost decisions for any application.

Fast mode is available for Claude Opus 5.5 on Claude Models on Google Cloud (Anthropic managed).

We've launched Claude Models on Google Cloud (Anthropic managed), the Claude API operated by Anthropic and reached through your Google Cloud project. Google…

A global map categorizing every 10-meter patch of land on Earth into distinct forest types.