Archive
Agent、MCP、coding agent、工作流自動化與評測。
代理工具
Cogram has introduced a cloud-based modeling environment shared by humans and AI agents, using FreeCAD 1.1, the OpenCASCADE geometry kernel, and an MCP toolset to work with 3D models and technical drawings. Agents can already complete constrained, iterative modeling tasks, but engineers must still inspect complex models for geometry, dimensions, and solid constraints.
GitHub Repo
OpenMAIC 1.0 expands its one-shot lesson generator into a course agent that can plan, revise, and resume work, with sessions stored through event streams and PostgreSQL. The new release provides 20 built-in skills and a vendor-neutral tool interface, but public deployments must still add identity isolation and scheduling for long-running media tasks.
AI 安全
Fetchgate performed read-only handshakes with 15,329 remote URLs in the official Registry and found that 5,462 reachable endpoints sent server-level instructions. The issue extends beyond prompt injection to include recurring context costs on every turn and hidden priority conflicts among tools.
代理工具
The new Channels feature can retain up to eight named sessions scoped by channel, chat, and sender, and reconnect to the original conversation after a session is closed. This is multi-task management, not parallel isolation: only one task can currently be selected at a time, and all tasks still operate in the same working directory.
硬體
Sopro V2 Turbo distills a 500M-parameter teacher into a 120M-parameter model, then uses reflow to reduce acoustic solving from 32 steps to two. The model can produce its first audio chunk in about 300 milliseconds on an M3 CPU and supports in-browser inference, but it currently covers only four European languages and does not include training code.
最新模型
Google has promoted Gemini Omni 1.1 Flash to a stable API. Scene extension can analyze the preceding ten seconds of content and generate videos segment by segment up to a total length of 40 seconds. The new version also supports first-and-last keyframes, 360p drafts, and 4K output, although the publicly available quality data still relies primarily on Google’s own evaluations.
代理工具
Researchers from Google and Purdue University designed an agent that reads only a fixed skill specification, its current state, and the latest observation at each step, immediately discarding its reasoning history after validating state updates. In a 100-step warehouse test, it achieved 0.94 accuracy using 65,408 tokens, but its effectiveness depends on a predefined state structure preserving information needed later.
最新模型
Tencent has released Hy4 Preview’s Apache 2.0-licensed weights, an FP8 version, and deployment recipes for vLLM and SGLang. The model activates roughly 49B of its 770B parameters per token. It supports a 1-million-token context window, though evidence for its quality and self-optimization capabilities still comes primarily from Tencent’s internal evaluations.
代理工具
Hugging Face and Voice Arena have expanded the open speech recognition leaderboard with the Monsoon dataset. Four public and private splits cover 4,888 speakers. For Hindi, reference lattices that accept multiple spellings replace a single canonical transcription, preventing conventional WER from counting correct recognitions as errors.
代理工具
Lemmalog separates agent memory into facts extracted by an LLM and verifiable state maintained by a rules engine. Preliminary evaluations show that it can substantially reduce context at answer time, though overall accuracy remains constrained by fact extraction and entity alignment.
最新模型
FastVideo combines DMD2 distillation with 90% sparse attention to reduce the base model’s 49 DiT calls to four, while releasing the full weights and LoRA. Its real-time generation figures depend on eight B200 GPUs, specialized VSA kernels, and fully warmed-up tests; a single GPU and mainstream consumer GPUs have yet to achieve comparable speeds.
AI 安全
After strengthening local inference and state-drift validation in 0.0.113, NVIDIA has further bound sandbox, inference service, and lifecycle permissions to persistently verifiable identities, preventing retry or recovery operations from taking over an environment with the same name but a different identity.