代理工具

Agent、MCP、coding agent、工作流自動化與評測。

QuantiBias Finds Quantized Models Can Pass Short-Form Safety Tests Yet Still Produce Stereotypes in About a Quarter of Open-Ended Responses

QuantiBias holds the model and prompts constant while varying only weight precision, measuring multilingual open-ended bias, refusals, and multiple-choice performance before and after quantization. The authors find that common short-form safety metrics remain broadly stable, yet an independent judge model still classifies about 24% to 27% of open-ended responses as endorsing stereotypes.

2026-07-26

機器人與模擬

NVIDIA Open-Sources Medical Robotics Physics Simulation Framework, Training Catheter Policies Across 8,192 Parallel Environments

NVIDIA has integrated Medical Physics Simulation into Isaac for Healthcare to simulate blood vessels, flexible instruments, contact friction, and X-ray sensing, then train robotic policies in GPU-parallel environments. An official demo reduced one training workload from more than five hours to under two minutes, but simulation speed does not equate to clinical efficacy or safety certification.

2026-07-26

代理工具

GitHub MCP Server Adds Early Support for Stateless MCP, Removing the Connection Phase and Shared Session Storage

GitHub MCP Server now supports the MCP `2026-07-28` specification, scheduled to be finalized on July 28. Remote requests no longer depend on the `initialize` handshake or protocol-layer sessions. The new design simplifies horizontal scaling, but compatibility work remains for Tasks, error codes, and custom clients.

2026-07-26

AI 安全

32 Kimi K3 Agents Collaborate to Uncover Redis Memory Vulnerabilities, Prompting Fixes Across Multiple Release Branches

Researchers claim that 32 Kimi K3 agents automatically generated fuzz harnesses, analyzed crashes, and built Redis remote code execution PoCs, with the fastest exploit chain completed in 27 minutes. Redis has patched the related `RESTORE` memory issues, but exploitation requires valid credentials and specific command permissions, while claims about the agents’ autonomy and “19 zero-days” still rely primarily on the researchers’ own account.

2026-07-25

代理工具

Alibaba Open-Sources Open Code Review, Using a Deterministic Pipeline to Constrain LLM Review Scope and Comment Placement

Open Code Review delegates file filtering, rule matching, and comment placement to deterministic code, then lets LLM agents search repository context and identify defects. Alibaba’s internal benchmarks show token usage at roughly one-ninth that of Claude Code, but it trades lower recall for higher precision and cannot directly replace existing tests and static analysis.

2026-07-25

代理工具

Antigravity CLI 1.1.6 Switches to Markdown-Defined Custom Agents, Bringing Tool Inheritance and Command Policies Under Version Control

Google Antigravity CLI adds a mechanism for creating main agents and subagents with `agent.md`, with frontmatter controls for MCP inheritance, visibility, and command execution policies. The new release also improves code search streaming and agent monitoring, though whether file-based policies can provide a reliable security boundary still requires testing.

2026-07-25

Microsoft Launches MAI-Image-2.5-Pro and MAI-Voice-2-Flash, Using In-House Models to Separate the Quality and Cost Curves

Microsoft is bringing its highest-quality image generation model and a high-throughput voice model into public preview in Foundry simultaneously, targeting precision editing and real-time voice agents, respectively. The company has published cost and latency data from several production environments, but cross-provider comparisons still lack consistent, reproducible testing conditions.

2026-07-25

SGLang-Omni Integrates MOSS-Transcribe-Diarize, Bringing Multi-Speaker Transcription to Continuous Batching

SGLang-Omni has added a deployment path for MOSS-Transcribe-Diarize that returns segment-level timestamps, text, and speaker labels in a single response through an OpenAI-compatible endpoint. This makes the open 0.9B model easier to deploy in online services, although the three evaluation datasets used for the official performance results are not currently fully public.

2026-07-25

Solar Open 2 Extends a 250B MoE’s Context to 1 Million Tokens With Hybrid Linear Attention

Upstage has released the weights for Solar Open 2, which uses 250B total parameters and activates 15B parameters per token for long-horizon agentic workflows. The model retains softmax attention and a KV cache in only one-quarter of its layers, but its million-token capability and Korean office-agent results are still based largely on the team’s own evaluations.

2026-07-25

代理工具

Meta AI Connects to Gmail and Google Calendar as Muse Spark 1.1 Begins Running Cross-App Personal Workflows

Meta has deployed Muse Spark 1.1’s planning and tool-use capabilities to Meta AI, enabling the assistant to read email and calendars and create persistent outputs such as presentations. The update expands the private context accessible to the model, but the company has not disclosed tool permissions, revocation mechanisms, or end-to-end task success rates.

2026-07-25

代理工具

Grok Build Workflows Breaks Down Coding Tasks Across Up to 1,024 Agents, Adding Staged Verification and Resumable State

SpaceXAI has added Workflows to Grok Build, allowing a single background job to dispatch up to 1,024 agents in parallel across multiple stages before aggregating and verifying their results. Workflows can be saved as shared team commands, but the company has not disclosed costs, success rates, or evaluations of error correlation in large agent swarms.

2026-07-25

代理工具

TRL Integrates OpenEnv, Enabling GRPO to Directly Train Stateful Tool-Using Agents

Hugging Face has added native OpenEnv integration to TRL, allowing GRPOTrainer to access multi-turn environments through a unified factory interface instead of treating each tool call as an independent function. Environments can run as WebSocket services or inside containers, but the project remains experimental, and users must verify isolation strength and reward integrity themselves.

2026-07-25