代理工具

Agent、MCP、coding agent、工作流自動化與評測。

T1 Replays MoE Routing to Stabilize Long-Horizon Reinforcement Learning, Raising Terminal-Bench 2.1 Success Rate to 64%

T1 records and replays MoE expert selections for every token, preventing numerical differences between rollout and training from sending them through different subnetworks. Its open weights support self-hosting, but benchmark results and competitor comparisons still come mainly from the team’s own evaluations.

2026-09-12

AI 安全

GitHub Copilot Lite Switches to Multi-Agent Reviews and Lets Reviewers Run Builds and Tests

GitHub has converted its lowest-cost Lite review into a multi-agent ensemble, with 47% more high-severity findings adopted in official experiments. Review agents can now also execute shell tools, making runner isolation, prompt injection, and audit logs for automatic resolution more important.

2026-09-12

最新模型

X-AuT Progressively Prunes Qwen3-ASR’s Audio Tower, Cutting In-Vehicle Encoding Latency by 21.4%

XPeng uses behavioral probes, cross-scale distillation, and LoRA to shrink the Qwen3-ASR-0.6B audio encoder from 18 layers to 14. The weights and inference code are public, but the full distillation pipeline and more than 280,000 hours of training data have not been released.

2026-09-12

AI 開發平台

OpenAI Agents API Turns the Codex Execution Framework Into a Managed Service, While Sandboxes Can Still Be Deployed in Your Own Environment

The public beta provides managed sessions, context compaction, tool orchestration, and sub-agent delegation, eliminating the need for developers to maintain agent loops themselves. Execution can take place in an OpenAI sandbox, on your own infrastructure, or through a partner provider, but versions, permissions, and usage costs must still be controlled separately.

2026-09-12

代理工具

Cursor Projects Uses a Persistent Coordinator Agent to Manage Months-Long Development and Can Launch Thousands of Subagents Based on Events

Cursor is expanding the unit of work for coding agents from a single conversation to a Project that can span multiple PRs and continue for months. A coordinator agent maintains shared files, delegates work to cloud and local agents, and automatically starts tasks in response to Slack messages, schedules, or PR events.

2026-09-12

AI 安全

GitHub Opens AI Scan Management API, but AI-Detected Vulnerabilities Still Cannot Block Merges

GitHub has added organization- and repository-level REST APIs that let security teams programmatically deploy AI vulnerability scanning for pull requests at scale. The scans can cover languages and frameworks not supported by CodeQL, but findings are currently advisory only, consume AI credits, and cannot be added to rulesets as merge requirements.

2026-09-12

最新模型

Sakana Fugu Splits Cost and Capability Tracks, Delivers Multi-Model Orchestration Through a Single Compatible API

Sakana AI has launched Fugu Max and Fugu Ultra v2, optimizing multi-model orchestration along two separate tracks: lower cost and greater capability. Both retain an OpenAI-compatible interface, but the official benchmarks still combine Sakana’s own tests with vendor-reported results, providing insufficient evidence of cost advantages in real-world workloads.

2026-09-12

AI 安全

Anthropic Reveals Attackers Use Agents to Continuously Rewrite Malware, Letting One Person Target Dozens in Parallel

Anthropic’s new threat report shows that several types of attackers have upgraded Claude from a coding assistant into a schedulable attack-orchestration layer with persistent memory. Some workflows automatically modify, rebuild, and redeploy malware after detection, although humans still largely control target selection and the review of stolen data.

2026-09-12

AI for Science

ARCHE Lets Chemistry Agents Iteratively Eliminate Mechanistic Hypotheses Using Computational Results, but the Public Release Cannot Fully Reproduce the Paper

ARCHE integrates literature retrieval, competing hypotheses, electronic structure calculations, and reflective review into a resumable closed loop, while releasing 65 actions and data from three case studies. However, the archived data already differ from figures reported in the paper, and the specialized model weights, training data, and some chemical evidence were not released with the code.

2026-09-12

代理工具

Meta Lets a Recommender-Systems Research Agent Take Over Multi-Day GPU Experiments Across Servers, Cutting Operational Fixes to 0.5 per Run

Auto-RecSys links research ideas, distributed training, failure recovery, and results analysis in a dual-loop system that persists across sessions. In 31 internal experiments, operational fixes fell from 4.0 to 0.5 per run, but Meta has not yet shown that the agent’s proposed model changes can consistently improve recommendation quality.

2026-09-12

AI 安全

LiteLLM Testing Finds 9.6% of Public Gateways Accept Default Keys; MCP Flaw Can Turn Any Token Into a Valid Session

Wiz scanned 3,074 public LiteLLM instances and found that 294 accepted `sk-1234` or required no authentication at all, including 191 with no authentication configured. Newly disclosed real-world measurements show how an authentication bypass in older MCP implementations, Python-executing guardrails, and access to cloud metadata can be chained into a cross-layer attack path.

2026-09-11

最新模型

Azure Speech LLM 2607 Automatically Updates Speech Recognition, Phrase Lists Can Hint More Than 2,000 Entities

Microsoft has updated its managed LLM Speech offering, emphasizing recognition of mixed-language speech, proper names, and numbers, while claiming up to a threefold latency reduction versus version 2605 in some scenarios. The new model uses the existing Fast and real-time APIs but is deployed automatically on the server side, so teams operating existing voice agents must establish their own regression tests and version monitoring.

2026-09-11