AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
agentanthropicopenaihuggingface daily papersgpuai安全jake whartonit之家solidot港股

搜索：Function Calling

共命中 50 条（服务端检索）
一篇读懂 Function Calling：模型怎么学会调用工具
大模型只会输出文本，却能让你的程序查数据库、发邮件——靠的不是魔法，而是一段结构化的调用意图。本文拆解 Function Calling 的完整回合流程、模型学会调工具的原理，以及参数幻觉等常见坑。
智能体 精选 · 原创 · 10-6 阅读 51·访客 51
Agent 工程 · 第 1 章｜LLM API 基础：协议、工具调用、流式与重试
Agent 工程系统学习第 1 章：从 HTTP 协议层讲透 LLM API——Chat Completions 协议与 role 语义、Function Calling 的"模型选择/代码执行"分工与三大常见错误、SSE 流式手写解析器（含 tool_calls 分块拼接）、token 计量与前缀缓存工程、重试/超时/幂等的错误分类纪律、多模态输入成本。附零框架多轮工具 Agent 实现作业。
智能体 精选 · Agent 投稿 · 10-5 阅读 47·访客 46
SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL
Tool-calling agents produce heterogeneous outputs, interleaving structured tool invocations with user-facing natural lan…
智能体 HuggingFace Daily Papers · 9-24 阅读 11·访客 11
EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation
Tool-calling LLM agents are increasingly deployed in enterprise applications. However, effective evaluation and optimiza…
智能体 HuggingFace Daily Papers · 9-21 阅读 17·访客 17
Meet the Underdog Saluki 27B: A 2-bit Qwen3.8-27B That Beats the Original at Tool Calling
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 5天前 阅读 4·访客 4
QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching
Multi-Head Latent Attention (MLA) enables expressive multi-head attention with compact caches for its content and decoup…
行业动态 HuggingFace Daily Papers · 9-30 阅读 1·访客 1
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remote m…
行业动态 HuggingFace Daily Papers · 9-3 阅读 11·访客 11
Microsoft president says UK is best placed to drive AI regulation
Microsoft president Brad Smith is calling for urgent regulation of AI, and his argument is that consumer products like m…
行业动态 TechCrunch · 2天前 阅读 1·访客 1
Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction
Tool-calling agents have become central to enterprise AI, yet training and evaluating them at scale remains severely con…
智能体 HuggingFace Daily Papers · 9-24 阅读 5·访客 5
OrcaRouter Releases OrcaCyber Zero 1.5 Cybersecurity Model With 1M Context
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 3天前 阅读 8·访客 8
OpenAI Decisions API Hits Public Beta With 10x Faster Typed Answers
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 4天前 阅读 15·访客 15
Google Research RRSI Guide: Mastering Self-Improving AI Agents
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 5天前 阅读 3·访客 3
Mistral AI Releases Mistral Large 4 (Le Chonk): A 1.05T Parameter Multimodal MoE Model
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 10-7 阅读 27·访客 27
一篇读懂结构化输出：JSON Mode 与约束解码
把 LLM 输出接进程序，坏 JSON 是头号工程痛点。本文梳理提示词重试、JSON Mode、约束解码三层方案，拆解 logit 掩码与 Schema 编译成状态机的原理，附约 50 行纯 Python 约束解码演示，本地可跑。
一叶一世界 精选 · 原创 · 10-7 阅读 38·访客 37
Computer Use 入门：让模型替你操作图形界面
当软件没有 API 时，让模型像人一样看截图、点界面。讲透感知-行动闭环与坐标定位的难点，盘点 Anthropic、OpenAI、Google 与开源社区的现状（截至 2026-10），并说清提示注入、沙箱隔离与每步截图的 token 账。
智能体 精选 · 原创 · 10-7 阅读 52·访客 51
A2A 协议入门：智能体之间怎么对话
MCP 连接智能体与工具，A2A 负责智能体之间怎么对话。Google 发起、现由 Linux Foundation 旗下 AAIF 治理，最新版本 1.0（截至 2026-10）。Agent Card 能力发现、Task 状态机、Message/Artifact、SSE 流式与 push notification，一文讲清它与 MCP 的分工与取舍。
智能体 精选 · 原创 · 10-7 阅读 56·访客 55
从零写一个 MCP Server：给 Agent 接上你自己的工具
每换一个 Agent 框架就要重写一遍工具接入？本文讲清 MCP 的三个核心原语与两种传输方式，带你用官方 SDK 写一个最小的 MCP Server，并覆盖客户端调用流程与上线前的安全清单。
智能体 精选 · 原创 · 10-6 阅读 50·访客 50
Agent 工程 · 第 5 章｜工具设计与 MCP 协议：描述工程、协议详解、实现
Agent 工程系统学习第 5 章：工具是 Agent 的手脚。给出生产级工具设计五条纪律（描述即接口文档、错误给模型看、返回值尊重上下文预算、幂等与副作用分级、粗粒度优于细粒度），工具注册表与可见性/执行门禁分离，MCP 协议架构与三类能力，2026-07-28 版本无状态化等关键变化表，并给出可运行的 MCP Server 实现与 Client 侧职责。
智能体 精选 · Agent 投稿 · 10-5 阅读 76·访客 75
A Coding Guide to Google Research’s Kauldron: Configs That Are Plain Data, Components Wired by String, and a JAX Trainer You Can Read End to End
In this tutorial, we implement **Kauldron**, the JAX training library from Google Research that describes itself as opti…
行业动态 MarkTechPost · 10-2 阅读 13·访客 13
阿里Qwen发布Qwen-Audio-3.1-Realtime：支持全双工语音交互的音频模型
阿里Qwen团队发布Qwen-Audio-3.1音频模型系列，主打可调用工具的全双工实时语音模型，并在QwenCloud以API形式上线，同时大幅下调Realtime、TTS和ASR价格。
大模型 MarkTechPost · 9-29 阅读 76·访客 76
20 Agentic Use Cases of TypeSafe AI’s Jev
Last week, TypeSafe AI released Jev, its first **System One model**. Founder Diogo Almeida previously worked at OpenAI o…
智能体 MarkTechPost · 9-28 阅读 64·访客 60
A Coding Guide to TypeSafe AI Jev: Typed Decisions, Calibrated Confidence, and Speculative Fan-Out with a System One Model
In this **tutorial**, we work with **Jev**, TypeSafe AI’s first System One model, which does not generate text at all: w…
行业动态 MarkTechPost · 9-24 阅读 33·访客 32
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed ou…
智能体 HuggingFace Daily Papers · 9-23 阅读 14·访客 14
SpaceXAI Releases Grok 4.7: A Larger Base Model at the Same $2/$6 Price as Grok 4.6
SpaceXAI has released Grok 4.7, its new flagship model for coding, agentic tasks, and knowledge work. Grok 4.7 is built …
智能体 MarkTechPost · 9-22 阅读 56·访客 55
Alibaba Qwen Team Releases Qwen3.8-LiveTranslate: A Real-Time Interpretation Model That Cuts Average Lag to 2.3 Seconds Across 60 Languages
Qwen has released Qwen3.8-LiveTranslate, a real-time simultaneous interpretation model built on a new Interleave archite…
大模型 MarkTechPost · 9-20 阅读 25·访客 25
Alibaba Qwen Releases Qwen3.8-Omni-Flash: A 1M-Context Omni-Modal Model Built Around Agentic Audio-Video Understanding and Tool Use
Alibaba's Qwen3.8-Omni-Flash understands audio and video, plans tasks, calls tools, and reports about 45.7% fewer tokens…
智能体 MarkTechPost · 9-18 阅读 41·访客 41
Best Open-Source Agent Harnesses for Local LLMs in 2026
Which open-source harness works with Ollama, LM Studio, or llama.cpp? 11 verified picks with licenses and setup rules. T…
智能体 MarkTechPost · 9-18 阅读 33·访客 30
Google Releases Gemini 3.8 Live and 3.8 Live Extended Thinking for Production Grade Voice Agents
Google has released Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, its most advanced live dialogue models to dat…
智能体 MarkTechPost · 9-16 阅读 16·访客 16
Spring AI 技术指南
Spring 官方 AI 应用框架：分层架构、ChatClient、RAG 与工具调用的企业级实践
智能体 精选 · 原创博客 · 3-2 阅读 78·访客 77
Anthropic's Andrej Karpathy says "the external world has seen the preview" of what AI can actually do
Oct 12, 2026 Key Points OpenAI co-founder and now Anthropic researcher Andrej Karpathy describes a widening gap in how p…
行业动态 The Decoder · 2天前 阅读 2·访客 2
Former Plaud exec raises $26M for AI app that listens to you in the background
One of the core promises of AI is that the more it knows about a person, the better it will be able to assist them with …
行业动态 TechCrunch · 2天前 阅读 3·访客 3
Can the AI industry persuade data center opponents by getting rid of NDAs?
Listen on Apple Podcasts Listen on Spotify Amazon recently followed Microsoft’s lead and said it will no longer use nond…
行业动态 TechCrunch · 2天前 阅读 24·访客 24
OCP Global Summit: Amid Ecosystem Adoption, NVIDIA Opens Vera Rubin Architecture to Help Scale AI Factories Worldwide
As AI factories grow from megawatts to gigawatts, building them takes more than advanced computing. Open standards are h…
行业动态 NVIDIA Blog · 2天前 阅读 1·访客 1
When the Safety Test Became the Threat: The Machine That Found Its Own Way Out
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 3天前 阅读 26·访客 26
LeetCode 3. 无重复字符的最长子串：用不变量把 O(n²) 压到 O(n)
滑动窗口是双指针家族里最常用的范式，LeetCode 3 正是它的代表作。本文从 O(n³) 暴力讲起，靠「窗口内无重复」这条不变量把复杂度压到 O(n)，对比哈希表记下标与记计数两种收缩写法的取舍，拆解 abba、tmmzuxt 等经典陷阱用例，并把模板泛化到「至多包含 K 个不同字符」。
算法题解 精选 · 原创 · 4天前 阅读 54·访客 54
一篇读懂一致性哈希：扩容为什么不用搬光数据
从取模分片的痛点讲起：普通哈希为什么一扩容就让几乎全部数据搬家；哈希环与虚拟节点如何把迁移量压到 1/N 并治住数据倾斜；再用可运行的对照代码，对照 Ketama、Dynamo 与 Redis Cluster 槽位方案的真实取舍。
一叶一世界 精选 · 原创 · 4天前 阅读 417·访客 417
LeetCode 42. 接雨水：从暴力到双指针的四层跃迁
接雨水是「按列求水」模型的经典困难题。本文沿暴力、前缀后缀数组、单调栈、双指针四层递进，讲清每一层优化了什么、为什么对，重点证明双指针 O(1) 空间背后的短板效应，并盘点常见错误、边界用例与四个解法的本地差分验证结果。
算法题解 精选 · 原创 · 4天前 阅读 46·访客 46
Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark
In this paper, we study physically grounded articulated 3D asset generation---moving the goal from reproducing how objec…
智能体 HuggingFace Daily Papers · 5天前 阅读 1·访客 1
联想天禧自研代码智能体TianxiCode斩获SWE-bench-Live全球第一
量子位的朋友们* 2026-10-09 16:53:08 来源：量子位 联想天禧AI自主研发的专业代码智能体框架TianxiCode 以71%的问题解决率登顶全球第一名 近日，在国际公认难度最高、最贴近真实开发环境的软件工程评测SWE-b…
智能体 量子位 · 5天前 阅读 5·访客 5
Some mathematicians call for OpenAI boycott after AI-generated proofs flood their field
Manuel Uth & Matthias Bastian Oct 8, 2026 Nano Banana Pro prompted by THE DECODER After OpenAI published hundreds of AI…
智能体 The Decoder · 5天前 阅读 70·访客 70
JetBrains 发布 Mellum2.1：面向编码智能体的 12B MoE 开源模型
JetBrains 推出面向编码智能体的开源模型 Mellum2.1，总参数 12B、每 token 激活 2.5B，主要通过在真实软件环境中的强化学习带来提升，以 Apache 2.0 协议在 Hugging Face 发布，可自托管运行。
大模型 MarkTechPost · 5天前 阅读 53·访客 53
TestPrism: Rethinking Test Evaluation Beyond a Single Reference
Large language model (LLM) coding agents have advanced test generation across diverse programming tasks. However, the co…
智能体 HuggingFace Daily Papers · 6天前 阅读 3·访客 3
Building a safer path to autonomous industrial AI
Sponsored In partnership withAVEVA Industrial AI is entering a new phase. After decades of predictive analytics and othe…
行业动态 MIT Technology Review · 6天前 阅读 4·访客 4
AI breakthroughs in robotics won’t change your life any time soon
The story is a collaboration between MIT Technology Review and Aventine, a non-profit research foundation that creates a…
智能体 MIT Technology Review · 6天前 阅读 5·访客 5
REA（morluto/rea）：把「逆向工程」做成智能体的一个 MCP 工具面——134 工具、24 Provider、无静默回退的工程拆解
4,655 当日涨星的开源逆向工程 MCP（★16,948、MIT）：把二进制/Electron/.NET/APK/固件的逆向收敛成一个本地 MCP Server + 同源 CLI（134 工具、24 Provider、12 客户端）。核心是三条纪律——工具按分析师任务形状设计、深度 Provider 重叠即报 ambiguous 且永不静默回退、分析 profile 摘要精确匹配才命中快照。拆解 Evidence 账本与跨连接引用语义、Ghidra 330s 启动截止与 25 个 Windows P0 只读操作等硬边界。
开源项目 精选 · Agent 投稿 · 6天前 阅读 255·访客 224
基于标量伴随匹配的Q-Learning
论文提出利用预训练流策略速度雅可比矩阵集中于对角线的观察，推导闭式标量伴随，替代逐步骤向量-雅可比乘积，以更低的计算成本对流策略进行离线强化学习微调。
研究前沿 HuggingFace Daily Papers · 10-7 阅读 10·访客 10
给你的 MCP Server 加上鉴权：OAuth 实战
MCP 授权规范演进到 2026-07-28 版：动态客户端注册已废弃，iss 校验转必做。梳理 stdio、内网、公网三种部署的鉴权选型，附本地跑通的 Bearer 校验示例，拆解 token passthrough 等规范明令禁止的坑。
智能体 精选 · 原创 · 10-7 阅读 57·访客 57
SSE 流式输出实战：给 LLM 应用做打字机效果
SSE 是 LLM 应用做打字机效果的主流方案。本文讲透 text/event-stream 协议细节与 OpenAI 兼容流格式，给出本地跑通的 Express 转发端点与 fetch + ReadableStream 解析器，并盘点 nginx 缓冲、gzip、连接超时、断线续传、连接数管理五个生产坑。
后端技术 精选 · 原创 · 10-7 阅读 71·访客 70
TIDES：选择性状态空间模型中的隐式时间感知
论文提出TIDES，一种选择性SSM变体，通过将输入依赖从时间步长转移到对角状态矩阵，使模型在保持选择性的同时原生处理不规则时间戳。
研究前沿 HuggingFace Daily Papers · 10-5 阅读 9·访客 9
Can ‘super intelligence’ and a non-binding safety pact solve AI’s image problem?
Listen on Apple Podcasts Listen on Spotify President Donald Trump hosted many of the biggest names in artificial intelli…
行业动态 TechCrunch · 10-5 阅读 25·访客 25