Pai 的 AI 雷达
含近几日仍热话题，按时间衰减排序。今天先看 ToolJet/ToolJet，其次 YouMind-OpenLab/awesome-nano-banana-pro-prompts。并行还有 GitHub Copilot app for Beginners: Using the diff, terminal, and browser、AI Scan for pull request APIs in public preview。
You can now use cache-mode to apply least-privilege access to the GitHub Actions cache at the workflow or job level. By granting each workflow or job only the cache access it needs, you can prevent unnecessary restores or saves and help protect trusted workflows from cache poison
We have deprecated MAI-Code-1-Flash across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions) today, September 10, 2026. Model Deprecation date Suggested alternative MAI-Code-1-Flash 2026-09-10 MAI-Code-1.1-Flash Pleas
GPT‑Live‑1 brings natural, full-duplex voice conversations to the API, with stronger instruction following, custom voices, and telephony support.
Build and launch cloud agents with the Agents API, a managed service powered by the Codex harness for orchestration, long-running sessions, and tool use.
A refreshed repository-level pull request listing page is now in public preview for all GitHub users. It brings powerful filtering, compact presentation mode, and more. Highlights The new page makes it easier to find and act on pull requests in a repository, with new filtering an
Meet the Data agent in ChatGPT Work. Connect company data, uncover insights, and build interactive dashboards with AI using natural language.
arXiv:2609.10024v1 Announce Type: new Abstract: Robot Operating System 2 (ROS 2) standardizes application code against a middleware interface (RMW) whose reference implementations are built on the Data Distribution Service (DDS). We present AXON, an alternative ROS 2 RMW implemen
arXiv:2609.05736v2 Announce Type: replace Abstract: LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model: prompts, tool interfaces, middleware, state handling, and recovery logic. We study this setting as resource-bounded harnes
arXiv:2609.10132v1 Announce Type: cross Abstract: The development of generative artificial intelligence resources enables opportunities of speeding up systems and engineering design work. This contribution introduces a framework of formal operations for assembling context in LLM
arXiv:2607.27231v3 Announce Type: replace Abstract: Modern AI systems depend on specialized accelerator kernels, whose development is complicated by increasingly diverse operators and hardware. LLMs and agentic systems promise to automate this work, but existing evaluations do no
arXiv:2609.09565v1 Announce Type: new Abstract: Agentic graph learning (AGL) has recently achieved promising results on graph reasoning tasks, where an agent powered by a large language model (LLM) sequentially samples the graph as evidence to support its final prediction. Existi
arXiv:2609.09856v1 Announce Type: cross Abstract: The rapid adoption of generative AI tools such as ChatGPT has sparked intense debate about their risks and opportunities for education, as well as the ways researchers should investigate them. In this paper, we approach these disc
You can now validate your Apple apps against macOS 27 using the Xcode 27 runner image for GitHub-hosted macOS runners, available in public preview. The image previously ran on macOS 26. How you target the image stays the same. Keep using the following labels in your workflow’s ru
arXiv:2609.09890v1 Announce Type: new Abstract: Multi-view diffusion models have shown strong performance in scenes with strong geometric priors and sparse semantics, such as indoor rooms or simple outdoor environments (e.g., fields, courtyards). However, they often fail to maint
arXiv:2609.08977v2 Announce Type: replace-cross Abstract: In this work, we present Gander, an end-to-end model that unifies omni perception, realtime interaction, and agentic capabilities within a single framework. In contrast to turn-based conventional paradigms, Gander continuo
OpenAI and GSA will offer eligible federal, state, local, and tribal governments $0 license fees, 50% off usage, and expanded cyber defense support.
If you administer GitHub Copilot Business or GitHub Copilot Enterprise, you can now centrally control which agent operations are blocked, require human approval, or can proceed without a prompt. Managed permissions cover shell commands, file reads and edits, and network domains.
arXiv:2609.10187v1 Announce Type: new Abstract: In this work, we introduce language-aligned motion representations for domain-generalizable UPDRS-Gait severity estimation, aiming to learn semantically structured motion features that generalize across heterogeneous clinical domain
arXiv:2609.10248v1 Announce Type: cross Abstract: Traditional software delivery assumes a static paradigm: code is constructed prior to execution and deployed as a fixed artifact. We present Agentic Just-In-Time Software Construction (A-JIT), a paradigm that replaces static binar
arXiv:2609.09875v1 Announce Type: new Abstract: Existing evaluation frameworks mostly assess only one part of AI agents, such as task completion (AgentBench) or security robustness (AgentDojo, ASB), rather than the complete pipeline of planning, tool selection, tool execution, me
arXiv:2609.09503v1 Announce Type: new Abstract: Rapid bespoke commissioning of the Cognitive Digital Twin (CDT) is a major challenge in reconfigurable manufacturing. Traditional digital twin (DT) construction methods primarily focus on geometric reconstruction, often neglecting t
arXiv:2609.09374v1 Announce Type: new Abstract: Arctic maritime navigation is becoming increasingly important as changing sea-ice conditions expand seasonal accessibility while simultaneously introducing substantial operational, environmental, and community risks. Arctic route pl
arXiv:2609.09404v1 Announce Type: cross Abstract: Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services. Most of these agents also read images, which gives an attacker a way to put text into the agent's context with
arXiv:2609.10008v1 Announce Type: new Abstract: Composed video retrieval (CoVR) searches a gallery for the target video that realizes a natural-language modification of a source clip. However, at gallery scale, this creates a fundamental tension: compact embeddings enable efficie