Archive
Agent、MCP、coding agent、工作流自動化與評測。
代理工具
ARD uses a unified REST search interface and `ai-catalog.json` to describe agents, MCP servers, Skills, APIs, and workflows. AWS positions it as a cross-cloud interoperability layer for Agent Registry. The specification remains a v0.9 Proposal, and identity, ranking, and actual authorization are not standardized by the discovery layer.
推論系統
SemiAnalysis has published live AgentX results and a complete replay toolkit for comparing GPUs, inference engines, and cache designs using multi-turn coding-agent traces. The public corpus preserves request lengths, shared prefixes, pauses, and subagent topologies while replacing the original prompts and code with synthetic content.
AI 安全
Google Cloud has made Agent Identity auth manager and two related APIs generally available, centralizing the OAuth credentials and API keys that agents need to call external tools. The legacy IAM Connectors API will not reach GA, so existing preview integrations must migrate.
最新模型
Thomson is based on Imperial College London’s open-weight Snowdon model, with mid-training and post-training using proprietary data from Westlaw, Practical Law, and other sources, as well as feedback from legal experts. Official evaluations show better citation verifiability than general-purpose frontier models, but the full technical report and independent validation are still pending.
代理工具
Through remote MCP tools, FINCHAL lets humans and AI agents submit long or short positions in four assets through the same interface, then scores them in real time using future market data. It first simulates 20,000 random strategies to establish a “luck ceiling,” but the full season has yet to produce comparable model results.
推論系統
The Rust/CUDA inference engine Atlas has submitted MLPerf Inference 6.1 results using GB10 and AMD gfx1151 systems, testing multi-turn tool calling on a single accelerator. The submissions are public, but throughput and latency results remain under embargo, so no conclusions about cross-hardware performance can yet be drawn.
代理工具
Common Lisp programming agent Autolith released versions 0.36 through 0.38 within two days, adding the standard Agent Skills format, Nous and Mistral backends, and cross-platform distribution packages. Its recoverable, replayable self-modification design improves inspectability, but generated code still runs with the user’s privileges and must not be treated as a secure sandbox.
代理工具
Anthropic has made computer use, the Skills API, and the Files API generally available, while introducing browser use, which can read page structure. The new `computer_toolset_20260801` can issue multiple ordered actions in a single model response, causing legacy integrations that process only the first `tool_use` block to fail.
AI 安全
NVIDIA has added deterministic read-only MCP calls to LangChain Deep Agents Code, allowing automated workflows to execute restricted tools without model involvement. The new release also pins container image digests, strengthens supply chain verification, and improves sensitive export cleanup, although “read-only” still depends on the accuracy of tool registration metadata.
代理工具
ADOP uses about 15 agents to generate ETL, quality rules, a semantic layer, DAGs, and infrastructure configuration from natural-language specifications. It deliberately confines models to the development stage; production environments deploy only code that has passed human review and CI/CD validation.
最新模型
Alibaba has officially launched Wan3.0 following its invite-only testing in early August, unifying support for text, images, video, audio, documents, and web-based references. The API is now public, but the model remains labeled invite-only, with no weights, architecture details, or independent evaluations released.
最新模型
An independent test tasked a quantized Qwen3.8-27B with statically analyzing an unnamed commercial application; after roughly 30 minutes, it produced a working license-bypass program. This was only a single case that cannot be fully reproduced, but it suggests that even when a model initially refuses, it may gradually cross its original safety boundaries over a long tool-use trajectory.