搜索“Agent”

flows; What’s New in version 1.0 Follow us on We’re excited to introduce the official release of LlamaIndex Workflows 1.0, a lightweight framework for building complex, multi-step agentic AI applications in Python and Typescript. We first introduced Workflows showcasing how to build reusable, event-driven applications powered by llama index . Since then, we’ve seen a growing need for developers to define complex AI application logic for agents without losing control of the execution flow. This f

匹配字段正文

zing the core primitives of RAG: chunking, embedding, indexing, and retrieval. For basic question-answering workloads, that foundational blueprint worked perfectly. But enterprise agents have completely outgrown it. Traditional RAG treats data access as a static, one-shot preprocessing step. It pulls a handful of context fragments, bundles them into a prompt window, and blindly hopes for the best. Autonomous agents cannot navigate an unstructured corpus through a fuzzy semantic search bar. They

匹配字段正文

al unstructured documents, spreadsheets contain highly structured numerical data, complex formatting, and visual hierarchies that traditional text parsing cannot capture. LLMs and agents need to understand not just the raw cell values, but the semantic relationships, formatting patterns, and hierarchical structure encoded in these documents. The challenge is that "messy" spreadsheets often use visual formatting (bold headers, colored cells, merged regions) to convey meaning rather than explicit

匹配字段正文

We’re building an automated AI engineer that dramatically improves performance of LLM agents on every single benchmark we’ve tried. TensorZero Autopilot is an automated AI engineer that analyzes LLM observability data, sets up evals, optimizes prompts and models, and runs A/B tests. It’s powered by our 11.5Kopen-source LLMOps platform that unifies an LLM gateway, observability, optimization, evaluation, and experimentation. The open-source project is used by companies ranging from frontier AI st

匹配字段正文

. Catches KV cache bugs and quantization degradation that short benchmarks hide; K2VV ToolCall: Measures trigger consistency (F1) and JSON Schema accuracy. Tool errors compound in agents; we catch them early; SWE-Bench: Full agentic coding test. (Not open sourced due to dependency of sandbox) Upstream Fix: We embed with vLLM/SGLang/KTransformers communities to fix root causes, not just detect symptoms. Pre-Release Validation: Rather than waiting for post-deployment complaints, we provide early a

匹配字段正文

碰撞、光线变化，各种突发情况每秒钟都在发生。 传统的端到端模型，比如VLA方案，虽然学得很快，但在面对长流程任务时，有一个致命弱点，那就是误差累积。 第1步有点小偏差，第2步偏差变大，到了第10步，整个动作可能就已经彻底变形了。更要命的是，单一黑盒模型在遇到干扰时，它不知道到底发生了什么，往往只能硬着头皮继续往下按原计划推，或者直接崩溃停机。 而另一种常见的Agent方案，虽然会做步骤拆解，但它的思考逻辑基本停留在纯文本或者多模态大模型的概率推理上。 每次环境一变，它得先把画面转成文本，等模型在那慢吞吞琢磨「下一步该干嘛」，等你推理完了，手可能早就被门夹到了。。。 CRIS-0展现出来的这种抗干扰和连贯性，背后到底是怎么做到的？ 在CRIS-0的系统里，有一个非常底层的改变，叫做统一状态与因果变量。 以前的机器人看世界，看的是密密麻麻的图像像素。但在CRIS-0眼里，它关心的不是世界表面长什么样，而是任务到底进行到了哪一步，任务本身就是一个因果状态进度条。 举个特别接地气的例子，比如机器人去铺桌布。 它不会傻乎乎地去计算整张桌布每个像素的坐标，而是实时追踪几个核心因果变量。比如桌布有没

匹配字段正文

Why the database is the overlooked bottleneck when running coding agents in parallel, and how Lakebase copy-on-write branching (sub-second, scale-to-zero) gives every agent an isolated database; An end-to-end development loop: Git worktrees + a Claude Code hook that auto-creates a Lakebase branch per agent, then GitHub Actions that create an ephemeral branch per PR, run Drizzle migrations, deploy a preview app on Databricks Apps, and post a schema diff; Further branching workflows: point-in-time

匹配字段正文

del. At the same time, the Chinese vendors are pressuring providers of proprietary AI models, such as Anthropic, to make their models more accessible to enterprises Related:Nvidia agent safety push raises questions about who governs AI autonomy Cybersecurity verification program This tension is evident in Anthropic’s decision to expand its cyber verification program on October 6. Anthropic originally introduced the CVP in April alongside Project Glasswing and Claude Mythos. The expanded CVP prov

匹配字段正文

ICYMI we've cut the price of Sonnet 5.5 cache reads in half. In the Claude Platform, it's now $0.10 per million tokens (input is $2, output is $10). This means Sonnet 5.5 now runs 20% cheaper on most agentic work. (API only, no change to Claude Code usage limits.)

匹配字段正文

At a Google Cloud event on Thursday, the company announced it’s bringing its Gemini AI into the agentic age, with the launch of a unified agent that can not only answer questions but also get things done on the user’s behalf, all from a single interface. The move comes as AI tools have been moving beyond being just conversational experiences to those that can take ownership of assigned tasks, generate code, schedule meetings, book appointments and travel, and more. It also follows the rise of co

匹配字段正文

Great to be with 700+ @googlecloud customers at the historic NASA Hangar One for Gemini at Work! Today, we introduced the new Gemini agent, a single, universal agent for work that has all of your business context and answers your questions, handles your knowledge work, creates your images and media, and writes and runs code - all from a single prompt box. It is connected to your personal workflows, your systems of record, and your enterprise controls. It’s built around a few core architectural p

匹配字段正文

The standard way to keep an AI agent in line is to have a second AI read over its shoulder . It’s been the default approach, but it can get expensive fast when agents run for hours and process the equivalent of several novels’ worth of text. Goodfire, a startup focused on interpretability (figuring out how AI models work internally), launched a cheaper option on Thursday: monitors that watch what’s happening inside an AI model as it works, rather than just reading what it writes. The monitors ar

匹配字段正文

live order books, per-provider and per-model quotes, and cleared transactions. That level of market data is unusual for an LLM API. What do buyers get? Drop-in compatibility with agentic coding tools. The post lists Claude Code, Codex, OpenCode, Cursor, Pi and Cline; Free email signup. The first 500 users get $20 of free inference, per Harrison; A referral program: 20% of referred fees as free inference, plus 10% on second-level referrals What do inference providers get? Providers onboard throu

匹配字段正文

微软于2026年10月7日宣布，面向AI代理的策略驱动型容器“Microsoft Execution Containers”（MXC）已正式发布。 Microsoft Execution Containers: Policy-driven containment for AI agents - Windows Developer Blog MXC is now GA on Windows 11. 🔐 Define which files and networks agents can access, with policies enforced at runtime. It’s part of how Windows is building the most secure platform for agents. Learn more: https://t.co/0JVVnARvLS https://t.co/wWuYmkK0NK— Windows Developer (@windowsdev) October 7, 2026 MXC是在2026年6月该公司活动“Build 2026”

匹配字段正文

Framework: ML Drift adopts a modernized custom op framework that provides direct registration APIs with low-level shading language access. To accelerate this, ML Drift includes an agentic SKILL.md guide, enabling coding agents to author, register, and verify performant custom shaders in minutes. This provides developers with granular control to integrate specialized model blocks directly into the execution graph, drastically reducing the barrier to deploying proprietary architectures. 5D Tensor

匹配字段正文

Back in June, Nvidia announced that it had secured agreements with Microsoft and a host of other PC makers to develop AI- and agent-ready PCs for Windows based on its RTX Spark chip, but details on the machines were scant at the time. On Wednesday, at an event held in San Francisco during the city’s Tech Week, Microsoft revealed the specs and price for its new Surface Laptop Ultra . The PC comes in two base models, one that starts at $2,600 and one with a more powerful chip that starts at $3,700

匹配字段正文

ntelligence works, Jacob Andreou, Microsoft’s EVP of Copilot, walked through a video demo on stage asking Microsoft’s Autopilot tool to help with filing taxes. Andreou told the AI agent that he got an email from his accountant and asked Autopilot to get her what she needs. Autopilot then used Hybrid Intelligence to search across different folders to find the documents, rename the files, zip them into a folder, and draft an email to send to the accountant with the zip file attached. Features powe

匹配字段正文

ntelligence works, Jacob Andreou, Microsoft’s EVP of Copilot, walked through a video demo on stage asking Microsoft’s Autopilot tool to help with filing taxes. Andreou told the AI agent that he got an email from his accountant and asked Autopilot to get her what she needs. Autopilot then used Hybrid Intelligence to search across different folders to find the documents, rename the files, zip them into a folder, and draft an email to send to the accountant with the zip file attached. Months after

匹配字段正文

At a Microsoft event in San Francisco on Wednesday, Jensen Huang and Satya Nadella outlined how NVIDIA and Microsoft are co-engineering hardware and software for AI agents to run on Windows PCs. NVIDIA was founded because of Windows, Huang said. Now AI agents are coming to Windows. “If you look at the entire journey of our company, Windows was at the core of it,” Huang said, tracing back NVIDIA’s support for Windows and Microsoft over several decades. “If not for Windows there would be no GeForc

匹配字段正文

Today, one in three pull requests on GitHub involves an AI agent . A year ago, that number was fewer than one in 10. If that pace holds, within the next two years, most of the code pushed to GitHub could be written by an agent. Much of it may never be fully read by a human. If developers and agents move faster, we have a responsibility to ensure protection keeps up with the accelerated rate of code creation. That means preventing more leaks before they happen and making the response to exposures

匹配字段正文