Archive
Agent、MCP、coding agent、工作流自動化與評測。
最新模型
The new version combines layout parsing with a vision-language model to support cross-page tables and form-field extraction. The official evaluation changed some of its test coverage, and API model-version mappings should be checked before deployment.
AI 研究
The benchmark asks agents to install dependencies, debug issues, and run experiments themselves, then has an independent model audit the execution evidence. Public code and traces let developers trace points of failure, but the results remain limited by model coverage and single-run testing.
GitHub Repo
The new version uses system messages to convey tool changes, allowing agents to adjust their capabilities in stages and potentially preserve existing prompt caches. The feature is still subject to model, message-position, and cache-setting limitations, and no performance test data is available.
GitHub Repo
The new release wraps malformed or non-object JSON from historical tool calls in diagnostic data, preventing a subsequent request from being rejected because of stale arguments. The change preserves call-and-result pairing; actual task recovery rates remain unverified.
AI 研究
The research preserves raw trajectories from successful tasks and generates relevant summaries only when the next task arrives. The gains come from specific benchmarks and model configurations, and deployment assessments must still account for the memory curation model’s additional costs.
GitHub Repo
The release lets admins independently stop and start a selected agent on a shared gateway, with a persistent marker to retain its disabled state. Already-dispatched scheduled jobs continue running, and compatibility should be checked for older multi-process deployments.
GitHub Repo
The release centralizes E2B sandbox creation, reconnection, and proxy credential rotation. The feature is disabled by default and requires an external proxy; DNS and QUIC traffic fall outside this TCP channel.
AI 研究
The package deletes or truncates older content through an API proxy, bringing rule-based compaction to existing coding agents. The paper’s cost comparison uses an idealized caching model, and the published defaults differ from the experimental settings.
AI 研究
The method retains all recurrent steps, using early exploration to narrow the scope of subsequent attention computation. Performance figures cover only attention workloads; the quality drop at 4K context length and the public reproduction materials still require verification.
GitHub Repo
The release bundles Node.js and uv for both Intel and Apple Silicon, selecting the appropriate versions at startup. The desktop app remains an early preview, and full agent workflows and backend configurations require validation in actual deployment environments.
硬體
The SDK provides super resolution and frame generation interfaces for mobile games, along with native integration documentation. The initial frame generation implementation adds one rendered frame’s worth of input latency, so its benefits must be assessed alongside power consumption and image quality.
推論系統
Tests running DeepSeek-R1 on eight B200 GPUs show that confidential computing increases average per-token latency by less than 5%. The results depend on adjustments to memory transfers, kernel timing, and multi-GPU communication, and still require validation under actual serving workloads.