代理工具

Agent、MCP、coding agent、工作流自動化與評測。

Cloudflare Separates Search, Training, and Agent Crawler Controls, but Bing’s Training Opt-Out Signal Is Not Yet Automatic

Cloudflare has introduced “Disallow AI Training,” combining `robots.txt` preferences with network-layer classification so websites can remain indexed by search engines while opting out of model training. Existing settings will be migrated automatically, but support varies across Applebot, Googlebot, and Bingbot—and selecting Block by mistake could still directly sacrifice search visibility.

2026-09-17

AI 安全

Google Uses Three-Layer Trace Analysis to Audit Agent Behavior, but Anomaly Detection Happens After Tool Execution

Gemini Enterprise Agent Platform’s Agent Anomaly Detection asynchronously analyzes OpenTelemetry traces, tool parameters, and execution flows, then uses lightweight models and LLMs to identify anomalies. The private preview adds no latency to real-time requests, but the tradeoff is that it primarily provides post-event detection and requires storing raw telemetry containing prompt and response content.

2026-09-17

代理工具

GitHub Uses Agents to Rewrite the Copilot Runtime as 830,000 Lines of Rust, Eliminating Per-Client Node.js Overhead

Copilot’s shared agent runtime has migrated from TypeScript/Node.js to native Rust and can be embedded directly into SDKs for six languages through a C ABI. GitHub’s stress tests showed session throughput rising to 120 per second, though the figures come from internal tests that excluded model and network latency.

2026-09-17

LimiX-2 Uses Joint Mechanism Modeling for Tabular Data, With a Single 400M-Parameter Model Spanning Three Task Types

Rather than estimating only conditional labels, LimiX-2 learns the joint structure of features and targets from synthetic causal data. The team has released the weights and inference code, but the model is restricted to non-commercial use, and its leading results come primarily from tabular benchmarks run by the authors.

2026-09-17

代理工具

Foundry Toolkit 1.6.13 Adds Support for Non-ACR Private Container Registries and Changes the Windows ML Runtime

The new VS Code toolkit can deploy hosted agents from private container registries configured with a connection, while also adding an AMD NPU build of Fara 7B and a quantized Aion adapter. Windows ML has been upgraded to `windowsml` 2.3, requiring existing projects to review their execution providers and dependencies.

2026-09-17

代理工具

Audit of 254 Submissions Shows Top SWE-bench Verified Rankings Are No Longer Statistically Distinguishable

A new study analyzing per-instance results across four SWE-bench splits found that none of the 29 adjacent pairs among the top 30 Verified systems passed a paired significance test. Interactions between models and agent scaffolds can also exceed the gap between leaderboard leaders, so engineering procurement decisions should no longer treat decimal-point differences as stable rankings.

2026-09-17

AI 基礎設施

FlashVector Expands Performance Agents From GPU Kernels to the Entire Recommendation Model Serving Stack

Unity’s team introduced FlashVector, an agent that searches for performance bottlenecks across GPU kernels, computation graphs, Triton servers, and feature services. Production tests showed throughput gains of up to 2×, but the code, modification traces, and complete cost data have not been released.

2026-09-17

代理工具

Dream-RSI Turns Agent Search Histories Into a Replay Simulator to Rewrite Exploration Strategies Offline

Research teams including Google enable a fixed coding agent to repeatedly rewrite its search schedule instead of updating model weights. Tests across eight algorithmic, mathematical, and GPU kernel tasks show that it can reduce exploration costs, although replay can evaluate only branches already traversed in the recorded history.

2026-09-16

代理工具

ScienceBuddy Alternately Rewrites the Agent Harness and Model, Turning Research Interactions into Ongoing Training Material

ScienceBuddy converts researchers’ requests, feedback, and execution logs into tasks and scoring rules, then alternately optimizes the agent code and model. The team has released a simplified experimental framework, but the full code for the hosted workspace and evidence of long-term self-improvement remain unpublished.

2026-09-16

ModAR 先預測軌跡、語意與深度再決定動作，降低世界—行動模型對 RGB 的依賴

CMU 的 ModAR 以共享擴散 Transformer 依序去噪多種未來表徵，再生成機器人動作。小規模實驗顯示，結構化表徵比額外預測 RGB 更有用，但程式碼尚未公開，真實世界證據也只有三項雙臂任務。

2026-09-16

推論系統

MLPerf Inference 6.1 Adds End-to-End RAG and Edge Agent Tests as Benchmark Expands to Full Inference Pipelines

MLCommons is no longer testing only individual models. Inference 6.1 incorporates retrieval, reranking, generation, and multi-turn agent workflows. The new release also introduces an API-based client/server harness, signaling that data center benchmarking will shift toward the more production-like MLPerf Endpoints suite.

2026-09-16

代理工具

IBM Identifies Unstable Agent Steps From a Single Trajectory as ALTK-Evolve Turns Diagnostics Into Reusable Guidelines

IBM Research has added a Consistency Analyzer to ALTK-Evolve that uses controlled resampling to pinpoint decisions prone to changing across repeated runs of the same agent. In AppWorld experiments, it raised a GPT-4.1 agent’s five-run all-success rate from 53% to 69%, though the evidence remains limited to a single agent architecture and a simulated environment.

2026-09-16