Pai 的 AI 雷达
含近几日仍热话题，按时间衰减排序。今天先看 Build more responsive apps with the Decisions API，其次 Global default for Copilot features generally available。并行还有 frontman-ai/frontman、Meta API endpoints updated for Actions blob storage。
The Copilot impact dashboard now includes an “Industry comparison” section. Enterprises, and organizations that aren’t owned by an enterprise, can compare their Copilot agentic adoption and leverage with aggregated benchmarks from participating peers. Participation is opt-in and
Public monitoring is now available in public preview for GitHub Enterprise Cloud with data residency (GHEC DR). Public monitoring with data residency Public monitoring extends secret scanning beyond internal repositories by monitoring public commits across github.com, attributing
Two improvements make it easier to review pull requests in the “Files changed” page: You can save your whitespace visibility preference across pull requests New and deleted files now use the full width in split view Save your whitespace visibility preference Open Settings → White
arXiv:2609.31713v2 Announce Type: replace-cross Abstract: As large language models (LLMs) become capable of processing increasingly diverse modalities and longer temporal contexts, an emerging line of work is moving beyond fixed video-language inference toward agentic systems tha
arXiv:2610.28826v1 Announce Type: new Abstract: Automated judges of clinical artificial intelligence (AI) outputs are necessary, but large language model (LLM) judges are costly and slow at scale. We compared Jev, a decision language model that returns structured judgments, with
arXiv:2608.26950v2 Announce Type: replace Abstract: Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing math benchmarks evaluate only final answers. This outcome-oriented evaluatio
arXiv:2610.30042v1 Announce Type: new Abstract: Harness optimization, which improves an agent's prompts, tools, and workflows, is an increasingly effective way to enhance agents built on frozen or closed-source LLMs. Leading approaches such as the Darwin--Godel Machine and the Hu
arXiv:2610.29023v1 Announce Type: new Abstract: Large language model (LLM) agents are often improved by iterating until a fixed verifier is done. Once that verifier saturates, the loop has nothing left to climb. We instead score agents against the current population, and a frozen
arXiv:2610.29174v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made rapid progress in general visual understanding, yet they still struggle with fine-grained instance-level consistency verification, where the goal is to determine whether two images
arXiv:2610.29749v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate software engineering artifacts written in domain-specific languages (DSLs). Correct DSL instances usually must comply with not only the concrete syntax but also the ab
arXiv:2610.29139v1 Announce Type: new Abstract: Frontier black-box Large Language Model (LLM) agents are proficient at long-horizon reasoning and precise action generation. However, when it comes to a specific agentic task, they have no internalized knowledge of how that particul
arXiv:2610.16067v2 Announce Type: replace-cross Abstract: Agent evaluation harnesses are software: they run a test suite, drive a test input generator, and decide outcomes with a test oracle. We audit them for defects a score table cannot show. First, a systematic oracle-integrit
arXiv:2610.29407v1 Announce Type: new Abstract: Creative prompt expansion improved overall audiovisual quality scores over raw prompts in a controlled pilot of VideoGen Model 1, our post-trained version of MiniMax H3. We compared the raw, reformatted, and expanded versions of 30
Claude 官方宣布，下周起 Pro、Max 和 Team 套餐在 Claude 网页、桌面和移动端应用中的会话将默认以 auto mode 运行。auto mode 不再逐步请求用户批准，而是由自动检查拦截高风险操作，用户可随时切回手动模式。其引用的 Claude Code 更新提到 auto mode 用独立分类器审查 shell 命令，测试中拦截了 89% 的危险命令，手动批准为 14%。 🔗 阅读原文 via AIHOT · https://aihot.news/items/ybo2q5ug2e71tfuab9m1t128o
OpenAI 宣布基于 GPT-6 Luna 的 Decisions API 正式可用，用于分类、路由、评分等有界答案问题，速度最高比通过 Responses API 使用 GPT-6 Luna 快 10x。 🔗 阅读原文 via AIHOT · https://aihot.news/items/xffhf8h0e0r145getmi9k1zgs
arXiv:2610.29474v1 Announce Type: new Abstract: This paper proposes a refinement to existing vision-based portable pipelines for the recognition of graspable object parts. Such pipelines can effectively support automatic grasp selection and preshaping in upper-limb prosthetic dev
arXiv:2610.28432v2 Announce Type: replace Abstract: Classical robot navigation stacks are reliable but often require re-engineering for each new robot type and site. Learning-based navigation shifts this effort from hand-tuned parameters to data generation and training, where a p
arXiv:2610.29093v1 Announce Type: cross Abstract: We introduce MixAgent, an agentic pipeline for music post-production that follows the workflow of audio engineers to build interpretable and editable mixing plans guided by a reference song. A grouping agent first routes related i
arXiv:2610.29010v1 Announce Type: new Abstract: Radiation treatment planning requires balancing competing objectives to satisfy clinical criteria while accommodating physicians' preferences. This study aims to develop an evidence-driven, multi-agent compound AI system that integr
arXiv:2610.24858v2 Announce Type: replace Abstract: Reducing MRI acquisition time improves patient comfort, reduces motion artefacts, and increases scanner throughput. Clinical protocols often shorten acquisitions by sacrificing spatial resolution, particularly along the slice ax
arXiv:2610.28934v1 Announce Type: new Abstract: Coding agents now complete tasks autonomously, modifying real-world state such as artifacts, software environments, and configurations along the way. Yet they show limited backup awareness: recognizing that an action will modify sta
arXiv:2610.09800v2 Announce Type: replace Abstract: Surgical video generation holds substantial potential for surgical education, simulation, and data augmentation, yet generating surgical videos with realistic and clinically plausible motion remains challenging. Most existing me
arXiv:2610.28818v1 Announce Type: cross Abstract: As systems engineering (SE) shifts from monolithic systems to Systems of Systems, Mission Engineering (ME) has emerged as a new line of thinking in SE. Mission environments are uncertain and dynamic, and outcomes depend on how mis
arXiv:2608.12002v2 Announce Type: replace Abstract: While autonomous agents show promise for network operations, existing telecom troubleshooting evaluations fail to capture the partial observability and heterogeneity of real-world telecom environments. We introduce CTBench, a pu