Archive
Agent、MCP、coding agent、工作流自動化與評測。
AI 安全
Exclusion rules configured by Copilot Business and Enterprise administrators can now prevent the Copilot App and CLI from directly adding specified files to model context. The mechanism is not comprehensive data loss prevention or an execution sandbox; GitHub still lists gaps involving symbolic links, remote file systems, and indirect IDE semantics.
推論系統
HeadWiseKV stops retaining the same amount of history for every attention head. Instead, it uses offline calibration to assign multilevel windows to individual heads and actually reduces physical KV residency. In fixed-model tests, the paper extends the maximum successfully validated context from 114K to 161K, although the higher figures reported by the public repository rely on specific quantization settings and a single RTX 4090D.
最新模型
IFM has released six text models ranging from 0.9B to 375B-A23B, along with data recipes, intermediate checkpoints, training code, and agent post-training logs. After a reward-hacking audit, the largest model’s TerminalBench score fell from 70.2% to 66.9%, highlighting that reproducible releases must also address benchmark contamination.
代理工具
Agent tools can now determine context usage from `RunContext`, while applications can send custom state through the same event stream. The release also adds a provider for self-hosted vLLM and a policy for rejecting streams that lack a `finish_reason`.
AI 安全
Multiple CLI coding agents run Git status queries before trust confirmation, allowing executable repository configurations to run on the host with the user’s privileges. The attack does not propagate through a normal `git clone`, but can be triggered by delivering a complete `.git` directory via ZIP archives, synced folders, or USB drives.
醫療 AI 與物理導向學習
New research combines GPU pencil-beam calculations, two frozen neural priors, and a 1.36-million-parameter 3D U-Net in a shared CT/MRI workflow. On internal data, the 1%/1 mm gamma pass rate reached as high as 99.12%, but the results do not yet constitute cross-institutional or clinical-use validation.
代理工具
The new release uses `managedMcpServers` to centrally distribute HTTP/SSE tool endpoints and adds a permission policy for unattended hosts that does not wait for user interaction. The upgrade also changes how allowlists apply to managed servers; unless enterprises add a denylist, tools that were previously filtered out may begin loading again.
推論系統
`@huggingface/kernels` can dynamically load GPU operators from the Hub, complete with interfaces, tests, and WGSL implementations. In operator-level tests on an Apple M4, Hugging Face reported a 2.57× geometric-mean speedup, but the results exclude model loading, compilation, and data transfer costs.
最新模型
Tether AI Research has released AfriSLM, fine-tuned from Qwen3.5, alongside the 17M-to-43M-parameter AfriNano models designed for browsers and smartphones. The models cover up to 19 sub-Saharan African languages, but claims that they outperform larger baselines are based primarily on automated metrics and have yet to be validated by native-language experts.
代理工具
The new `langchain.mcp` provides a unified way to connect to one or multiple MCP servers and converts mid-execution tool prompts into resumable LangGraph interrupts. The interface remains in Alpha, with consecutive releases changing method names and elicitation behavior, so it is not yet suitable for stable production environments.
代理工具
Google is bringing automatic selection of Android-specific skills and on-device Gemma 4 inference to Android Studio’s stable channel. Code can remain on the developer’s machine, but local execution does not mean the agent has robust permission isolation or verifiable quality.
代理工具
GitHub now lets administrators decide whether Copilot may submit Approve reviews that count toward branch rules, with path-level restrictions available. The feature remains in public preview, and there is not yet sufficient accuracy evidence to treat model approval as an independent quality guarantee.