Archive
Agent、MCP、coding agent、工作流自動化與評測。
最新模型
Alibaba is moving Qwen3.8-Max to a production API, targeting software development and long-running knowledge work, while announcing plans to release weights for both the flagship and 27B models. The model ranks near the top of a community coding arena, but complete technical documentation on its architecture, active parameter count, and self-hosting costs remains unavailable.
AI 安全
CAGE does not merely inspect the tool response currently visible to an agent. It verifies that every plausible correct binding permits the same action. The research proves that checking categorical fields and numeric errors separately cannot guarantee safety when both change simultaneously.
代理工具
The compatibility period for `used_copilot_coding_agent` in GitHub Copilot usage reports expired on August 1. Integrations should migrate to `used_copilot_cloud_agent`. The two fields previously returned the same Boolean value, but the legacy field is no longer guaranteed after the deadline, potentially causing enterprise adoption reports to silently undercount usage.
GitHub Repo
NVIDIA, the Linux Foundation, Hugging Face, Microsoft, and other organizations have formed the Open Secure AI Alliance to address vulnerabilities in agents and AI software with open models and tools. Its first concrete contributions include NVIDIA’s NOOA framework, but the alliance has yet to announce common specifications, governance processes, or a delivery timeline.
AI 安全
New research suggests that the JSON-style tool specifications used by agents are not merely neutral interfaces and may suppress models’ internal refusal representations. By separately evaluating safety before execution using flattened text specifications, SafeKeep increased the average refusal rate for harmful requests from 23.8% to 70.6%.
代理工具
A Microsoft Research team jointly updates synthetic applications, tasks, and graders based on agent failure trajectories instead of merely adding more static webpages. The 9B model’s average success rate across 14 evaluations rose from 36.5% to 67.1%, although only four environments have been publicly released as benchmarks.
代理工具
Alibaba’s Qwen team has released a technical report on a GUI agent spanning mobile, desktop, web, and DeepSearch environments. Its unified action space combines on-screen interactions, CLI commands, and batched actions. The model leads existing systems on several self-reported benchmarks, but its weights, training data, and complete execution framework have not yet been released.
代理工具
Using 1,019 human-annotated trajectories spanning the web, Windows, Ubuntu, and mobile platforms, OSReward tests whether vision-language models can correctly determine whether computer agents have completed their tasks. The team also released 100,000 reasoning-based judgment examples and trained self-hostable 9B and 35B OS-Shepherd reward models.
推論系統
WIDE brings dynamic pruning down to token-level attention-head groups and FFN channel groups, supporting both prefill and decode. At 50% sparsity, the study reports up to a 4.95× decoding speedup for core layers, but the end-to-end gain falls to 1.55×.
AI 安全
The public review of the OWASP Agentic Skills Top 10 v1 draft has concluded. The framework organizes malicious skills, excessive permissions, dependency confusion, and cross-platform portability risks into ten control categories. It treats skills as the behavioral layer between models and MCP tools and proposes a universal format for declaring permissions, provenance, and integrity.
科學機器學習
UNICON converts data from rivers, traffic networks, power grids, weather systems, and human mobility into a shared graph-sequence interface, using a small number of numerical examples to specify new tasks in context. In unseen domains such as web traffic, the model approaches the performance of specialized models, but it has so far been validated only on forecasting tasks, and neither its weights nor code have been released.
AI 安全
A new study simulates auditing agent populations under limited human-review budgets and identifies the tipping point at which distorted self-reported confidence causes ranking-based strategies to underperform random sampling. Five small and midsize open-weight models achieved confidence AUROCs of only about 0.5 on two benchmarks, although the findings are based on a single prompt and direct-answer setup.