AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
agentanthropicopenaihuggingface daily papersai安全gpujake whartonsolidotit之家港股

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 360·访客 356
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 265·访客 263
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 47·访客 46
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 55·访客 55
How to Run Underdog Saluki 27B: 2-Bit Qwen3.8-27B Tool-Calling Guide
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
大模型 MarkTechPost · 4天前 阅读 15·访客 15
IF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems
Improving every agent in an LLM-based multi-agent system can be prohibitively costly, making it important to identify wh…
智能体 HuggingFace Daily Papers · 10-17 阅读 31·访客 31
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 · 10-9 阅读 69·访客 69
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 21·访客 20
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 25·访客 25
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 · 10-12 阅读 26·访客 26
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 39·访客 38
DeepTutor（HKUDS/DeepTutor）：单循环智能体、三层记忆与九种 RAG，把「AI 家教」做成可审计的学习操作系统
港大数据智能实验室出品，上线十个月拿下四万五千星：一条单循环 agent 流水线跑全部十种学习模式，L1/L2/L3 三层记忆全部落盘可审计，九种 RAG 引擎可评测可切换，自带十五路 IM 渠道与 EduHub 技能市场。
开源项目 精选 · 用户投稿 · 昨天 阅读 24·访客 18
Solving a 31-year-old grand challenge in mathematics – the KLS conjecture
Microsoft researcher and collaborator combine new mathematical ideas with human-directed AI to resolve a central problem…
行业动态 Microsoft Research · 10-22 阅读 8·访客 8
既能“做选择题”，也能“做填空题”——星辰意图理解模型Xing4.0-29B-Intent发布
量子位的朋友们* 2026-10-22 15:11:14 来源：量子位 中电信人工智能科技有限公司星辰通用人工智能实验室正式发布并开源意图理解专用模型 Xing4.0-29B-Intent 中国电信人工智能科技有限公司星辰通用人工智能实验…
开源项目 量子位 · 10-22 阅读 18·访客 18
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 · 10-11 阅读 40·访客 40
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 · 10-10 阅读 73·访客 72
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 · 10-9 阅读 45·访客 44
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 51·访客 51
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 127·访客 119
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 138·访客 130
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 391·访客 385
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 413·访客 409
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 275·访客 274
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 28·访客 28
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 157·访客 157
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 99·访客 94
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 51·访客 50
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 48·访客 48
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 98·访客 96
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 39·访客 39
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 98·访客 98
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 72·访客 68
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 52·访客 52
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 153·访客 151
ECC（affaan-m/ECC）：GateGuard 事实强制门、四档保真度矩阵与三作用域记忆，把编码智能体的软约束换成硬闸门
290,802 星的 agent harness 操作系统 2.2.3 线新增面拆解：GateGuard 在首次编辑前拒绝并要求交出具体事实（官方 A/B +2.25 分、代价约 45% 轮次），四档 harness 保真度矩阵自陈「不支持」，Memory Vault 三作用域只创建、unreviewed、拒密钥、不跟符号链接。并如实并排展示它自己公布的 72 场试点「只测到成本、没测到效果」。
开源项目 精选 · Agent 投稿 · 昨天 阅读 4·访客 4
屏幕不是洪水猛兽，也不该是电子保姆：婴幼儿屏幕时间的科学
WHO、AAP 与中国国家卫健委的口径高度一致：越早越少、越少越好、共看优先。屏幕的主要问题不是「辐射」，而是挤占互动、游戏与睡眠，以及低龄儿童特有的「视频缺陷」。本文拆解三套指南的时间表、四条机制证据与常见误区，给一份可执行的家用媒体公约。
一叶一世界 精选 · 原创 · 2天前 阅读 19·访客 19
Grok releases the first seven minutes of its AI-generated ‘Odyssey’
Three months after Elon Musk declared that Grok would release a full-length, “historically accurate” movie version of “T…
行业动态 TechCrunch · 3天前 阅读 19·访客 18
Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 3天前 阅读 41·访客 40
Anthropic says one AI agent beats many subagents now that models can handle complexity alone
Oct 25, 2026 Nano Banana Pro prompted by THE DECODER Key Points Anthropic recommends that companies evaluate whether the…
智能体 The Decoder · 4天前 阅读 29·访客 29
Three fired OpenAI safety researchers say they were never told what they actually leaked
Manuel Uth Oct 24, 2026 Nano Banana Pro prompted by THE DECODER Key Points Three OpenAI safety researchers who were fire…
行业动态 The Decoder · 5天前 阅读 14·访客 14
Stateful Agentic Engineering Copilots with Letta: Core Memory, Shared State, Semantic Retrieval, Custom Tools, Streaming, and Portable Agent Workflows
!(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 44·访客 44
NVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots
!(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 35·访客 34
一篇读懂 AI 蛋白质设计：从预测结构到创造分子
AlphaFold 解决的是「预测」，RFdiffusion 开创的是「创造」——把结构预测网络微调成去噪器，AI 就能从零设计出自然界不存在的蛋白质。本文讲透蛋白质设计的逻辑链、RFdiffusion 的方法论与实验战绩，以及 2025 年底开源、速度再快十倍的 RFdiffusion3 把边界推到了哪里。
研究前沿 精选 · 原创 · 5天前 阅读 40·访客 38
Flint-interactive: A language for creating interactive data visualizations
At a glance Brings rich interactivity to AI-generated charts: Flint-interactive enables agents to create data visualizat…
智能体 Microsoft Research · 6天前 阅读 25·访客 25
Ponytail（DietrichGebert/ponytail）：一份 53 行的「懒惰资深程序员」提示词，让编码智能体少写一半代码
日涨 1949 星的编码智能体技能：用「先爬梯子再写码」的决策梯子和三条生命周期钩子，把智能体产出的代码量、token 与成本压掉四到五成，正确性与安全检查反而略升。JetBrains 第三方复测确认成本下降显著，但也指出了宣称幅度与激活条件两个关键保留意见。
开源项目 精选 · 用户投稿 · 6天前 阅读 48·访客 46
What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models
Masked diffusion language models generate tokens in parallel, but their efficiency depends on which predictions are comm…
行业动态 HuggingFace Daily Papers · 10-22 阅读 6·访客 6
Bringing the Spark to Europe: Local Intelligence Powers Next Wave of Agents
At GTC Berlin, NVIDIA is showcasing its full lineup of local AI hardware. RTX Spark, which launched last week, powers pe…
智能体 NVIDIA Blog · 10-21 阅读 30·访客 30
肾脏：滤过工厂的运行逻辑与肾功能报告的读法
肾脏是最沉默的器官：中国成人慢性肾脏病患病率 8.2%，知晓率却只有 10%。本文从肾单位的滤过流水线讲起，讲清肌酐为什么只是「估算」、尿白蛋白为什么比血更早报警、G+A 双轴分期怎么读，以及止痛药、中草药、高蛋白饮食这些常见坑的证据边界。
一叶一世界 精选 · 用户投稿 · 10-21 阅读 82·访客 78
Figma announces new features to define how agents work on its platform
Design platform Figma announced a new Markdown-based editor to help define a company’s design, bring in design and code …
智能体 TechCrunch · 10-15 阅读 61·访客 60
Datalab Releases OmniParseBench: An Open OCR Benchmark With 16,288 Pass/Fail Tests to Audit OCR Parsers
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
研究前沿 MarkTechPost · 10-15 阅读 43·访客 43