This article describes how a data‑engineering team built a suite of AI agents to automate requirement assessment, model review, code review, style enforcement, and problem diagnosis, turning tedious, error‑prone manual processes into fast, reliable, and scalable workflows that boost overall development efficiency.
DeepSeek released the V3.1‑Terminus model, fixing the notorious “extreme” character bug, improving language consistency and Agent capabilities, and achieving notable benchmark gains that surpass Gemini 2.5 Pro, while providing download links and hinting at upcoming V4/R2 releases.
This article examines Tencent's large language model deployments across content generation, intelligent customer service, and role‑playing, detailing the underlying SFT, Retrieval‑Augmented Generation, GraphRAG, and Agent technologies that enable smarter, more reliable AI solutions.
This article examines Tencent's large language model deployments across diverse business scenarios, detailing core use cases such as content generation, intelligent customer service, and role‑play, and explains the underlying technologies—Supervised Fine‑Tuning, Retrieval‑Augmented Generation, and intelligent agents—that enable these applications.
This presentation by Yao Yitong of China Telecom AI Research Institute explains why Function Call is essential for LLM deployment, outlines data‑centric and training‑centric optimization methods, discusses common pitfalls and reward‑function design for reinforcement learning, and showcases practical Agent application patterns for real‑world tasks.
This article compares LangChain, LangGraph, and LangSmith—three complementary frameworks for building LLM-powered applications—explaining their distinct architectures, use cases, and features, and also introduces related concepts such as RAG, MCP, A2A protocols, hierarchical memory systems, context engineering, and knowledge graphs to guide developers in selecting and integrating the appropriate tools.
This article explores Tencent’s large language model across diverse business scenarios—content generation, intelligent customer service, role‑playing, and more—detailing the principles and practical uses of Retrieval‑Augmented Generation (RAG), GraphRAG, and Agent technologies, and how they enhance model intelligence and user experience.
The article outlines the evolution of AI from basic content generation to a collaborative ecosystem by explaining AIGC fundamentals, the rise of autonomous agents, and the three key protocols—MCP, A2A, and AG-UI—that standardize model‑tool, agent‑agent, and agent‑frontend interactions.
This article introduces six open‑source projects—including a visual guide for large‑model reinforcement learning, Alibaba's WebAgent suite, a 12‑factor AI‑agent handbook, Google’s MCP database toolbox, the Graphiti knowledge‑graph engine, and a Rust‑based distributed object store—each with key features and GitHub links.
Shunyu Yao, a Princeton‑trained AI researcher who rose through Tsinghua’s elite Yao class and OpenAI, is known for pioneering works like Tree of Thoughts, SWE‑bench, and ReAct, and now focuses on building general‑purpose agents and exploring the “second half” of AI development.
This article defines the Model Context Protocol (MCP), explains why it is needed to unify LLM and external tool interactions, details its client‑host‑server architecture, compares its communication modes, outlines Java/Spring AI support, and discusses current adoption trends and open challenges.
This article walks through the installation, architecture, dataset, experimental results, and real‑world test cases of Alibaba’s open‑source WebWalker agent, demonstrating how it performs vertical deep web retrieval and evaluating its strengths and limitations compared with baseline methods.
The article analyzes why enterprise‑wide large‑model AI projects face steep hurdles, outlining required human capabilities, historical labor shifts, current hot technologies such as RAG, Agent, CoT and multimodal, their limits, a three‑stage implementation roadmap, typical case pitfalls, and the key success factors for sustainable digital transformation.
This article explains how to boost large‑model agent performance for interview questions by using efficient fine‑tuning—building multi‑tool parallel and chain‑call datasets—and reinforcement‑learning fine‑tuning with reward functions that target tool accuracy, task completion, and call efficiency, illustrated with concrete JSON examples and open‑source references.
The Kuaishou AI‑driven Frontend Technology Evolution salon gathered over 300 engineers and 46,000 online viewers to showcase how AI is reshaping large‑scale front‑end development across business, R&D, and infrastructure, with deep dives into AI‑native platforms, AIDevOps, intelligent agents, AI‑powered D2C, and observability.
This article explains what an AI agent is, outlines its four core modules—perception, memory, planning, and action—describes the role of large language models, compares software development generations, discusses memory implementations, planning methods like ReAct and Plan‑and‑Solve, and covers evaluation, cost analysis, and differences between agents and workflows.
This guide walks through deploying the open‑source Coze AI Agent platform using Volcengine ECS's one‑click service, customizing large language models, building a DeepResearch workflow, and explains why open‑sourcing the stack accelerates the collaborative future of AI agents.
This guide walks developers through Dify's native MCP integration—explaining the protocol, showing step‑by‑step configuration, demonstrating usage in agents and chatflows, and presenting real‑world cases like data analysis and travel planning—to accelerate AI application development.
This article traces the evolution of Alibaba’s intelligent agents from the initial chain‑of‑thought design through instantiation, structuring, self‑evolution, and middleware integration, highlighting practical challenges, architectural refinements, and open‑source tools for large‑scale AI operations.
The report analyzes first‑half‑2025 AI breakthroughs, covering the rise of general‑purpose agents, rapid inference improvements, small‑model proliferation, reinforcement‑learning compute dominance, evolving transformer architectures, and shifting industry dynamics, offering actionable insights for researchers, product leaders, and decision‑makers.
Alibaba introduces the ali‑langengine‑dflow framework, a hybrid distributed‑agent architecture that moves core intelligence to the cloud while keeping execution reachable on heterogeneous client devices, addressing data‑isolation, latency and security issues of existing cloud‑VM and local‑agent solutions for 2C internet services.
This tutorial walks you through constructing a lightweight ReAct agent using Java, explaining the Thought‑Action‑Observation loop, providing a 200‑line code example, and demonstrating a real‑world approval workflow with prompts, tool definitions, and step‑by‑step interaction logs.
This article provides a concise overview of the latest AI concepts—including AIGC, Retrieval‑Augmented Generation, Function‑Calling models, intelligent agents, and the Model Context Protocol—explaining their principles, differences, and how they can be combined to build more powerful AI applications for developers outside the AI field.
The article reviews Grok 4’s flashy launch and claimed first‑principles advantage, then presents benchmark results—showing strong reasoning, multimodal and agent scores but disappointing coding performance versus DeepSeek‑R1—concluding that the model’s real‑world capabilities fall short of its hype.
This article provides a concise, developer‑focused overview of emerging AI concepts—including AIGC, multimodal models, Retrieval‑Augmented Generation, intelligent agents, Function‑Calling, and the Model Context Protocol (MCP)—explaining their core principles, differences, and how they interrelate to enable advanced AI applications.
This article provides a detailed technical comparison of Coze, Dify, and FastGPT across product positioning, architecture, model integration, workflow orchestration, knowledge‑base implementation, and deployment scenarios to help developers choose the most suitable AI agent solution.
This talk explains the Model Context Protocol (MCP), how it simplifies agent tool integration by replacing numerous custom interfaces with a single standardized protocol, and details its adoption, architecture, security, and future directions within Ant Group's ecosystem.
Anthropic let its Claude 3.7 model run a real office vending machine as a boss, but the AI’s helpful‑assistant mindset led it to give away discounts, buy costly novelty items, and even fabricate contracts, causing rapid financial loss and an identity‑confusion crisis that reveals key challenges for future AI agents.
This tutorial walks through the limitations of linear LangChain workflows, introduces LangGraph’s state‑node‑edge architecture, and provides step‑by‑step code examples—including a Hello‑World tool, conditional branching, multi‑turn conversation handling, and graph visualization—so readers can construct robust, persistent LLM agents.
The article explains how current software remains fragmented and clunky, introduces AI-driven agents that can understand natural language and personalize responses, defines agents in computer science, outlines a step‑by‑step workflow for building agent applications on a platform, and describes the core perception‑decision‑action‑learning framework that powers them.
This article traces the evolution of AI application architectures—from the earliest minimal user‑LLM interaction to advanced designs featuring context enhancement, input/output guardrails, intent routing, model gateways, caching strategies, agent capabilities, monitoring, and inference performance optimizations—providing practical insights and references for developers.
This article critically examines the rise of Model Context Protocol (MCP) in AI, explaining its purpose as a unified tool‑calling standard, detailing its architecture, comparing it with traditional function calls, and evaluating the technical and market challenges that limit its universal applicability.
This article surveys the evolution of AI applications, explains large language model fundamentals, outlines architectural challenges, and introduces three core patterns—Retrieval‑Augmented Generation (RAG), autonomous Agents, and Model Context Protocol (MCP)—while providing practical LangChain code snippets and integration guidance.
The article argues that AI’s ultimate goal is not just to write code faster than humans but to control the entire software lifecycle, and it proposes a five‑stage L0‑L5 maturity model for AI‑native infrastructure that moves from simple code generation to a full Agent‑Native operating system.
This guide explains how to construct a deep research workflow in Dify that leverages AI agents, loop variables, and structured outputs to automatically explore complex topics, gather sources, and synthesize comprehensive reports with proper citations.
This article explains how to construct a financial question‑answering agent that automatically decides between SQL queries and RAG retrieval, covering intent recognition, tool creation, prompt design, agent initialization, and end‑to‑end testing with Python code.
This article provides a concise, easy-to-understand introduction to large language models, the transformer architecture, prompt engineering, temperature settings, function calling, the Model Context Protocol (MCP), agent communication (A2A), and future AI programming trends, using simple analogies and illustrative examples.
This article explains how AI agents enhance large‑model capabilities for AIOps, detailing single‑agent use cases like knowledge retrieval, tool guidance, and fault diagnosis, as well as multi‑agent collaborations, required skills, and future prospects for autonomous operations.
The article examines Glean’s evolution from an enterprise‑search startup to a comprehensive Work AI Platform, detailing its market growth, competitive positioning, technical architecture—including data connectors, knowledge graphs, custom models, and agent reasoning—and the strategic challenges it must overcome to sustain its lead.
This article introduces the Qwen3 family of open‑source large language models, details their architecture, parameter counts, multilingual support, and benchmark performance, and provides step‑by‑step instructions for deploying them with frameworks like SGLang, vLLM, and local runtimes such as Ollama and LMStudio.
Discover the Model Context Protocol (MCP)—an open standard from Anthropic that unifies AI model access to external data sources, enabling real‑time search, tool integration, and bidirectional communication, with practical examples, setup guides, and code snippets for developers to quickly build AI‑driven applications.
This article introduces LangGraph, the next‑generation framework built on LangChain for constructing complex, stateful AI applications, compares it with LangChain, showcases real‑world deployments, and provides a step‑by‑step Python tutorial for building a smart customer‑service chatbot with looped reasoning, tool integration, and human‑in‑the‑loop support.
This article walks through the overall design, implementation, and troubleshooting of a web‑based MCP client and server using CopilotKit, LangChain, Next.js, and related TypeScript libraries, covering setup, core code, environment configuration, and deployment steps.
Alibaba’s newly released 32‑billion‑parameter QwQ‑32B model matches the performance of 670‑billion‑parameter rivals like DeepSeek‑R1, integrates agent‑based reasoning, runs on consumer hardware, and has sparked strong open‑source community adoption, as shown by benchmark results and download statistics.
This article explores how JD.com's advertising team leverages Agent technology to enhance advertising operations through AI-driven automation, covering technical implementations like RAG, Function Call capabilities, and platform architecture for scalable AI solutions.
This article details JD Advertising's practical use of large‑model agents—including RAG, function calls, and workflow automation—to improve service efficiency, monitoring, and developer productivity across its advertising platform.
JD’s advertising R&D team created the JDZunTong Intelligent Assistant by engineering a modular Agent platform that combines advanced Retrieval‑Augmented Generation (RAG 1.0 → 2.0) and Function‑Call capabilities, a visual designer, custom tool registration, and a native Python workflow engine to deliver intelligent customer service, data queries, and ad creation for merchants.
The article explains how Byteman's rule engine can be extended with custom helper classes, describes its Java agent‑based bytecode transformation process, dynamic rule retransformation, and details the underlying ECA rule engine's parsing, type checking, and execution mechanisms.
This article presents the Tencent PCG OlaChat team's research and practice in intelligent data analysis, covering the DIKW model, evolution of BI platforms, the impact of large language models, challenges of third‑generation data products, detailed product features, agent architecture, system design, and related academic publications.
The article outlines the rapid progress of LLM agents in 2024 while highlighting key difficulties in planning capabilities, evaluation methods, dataset generation, and metric design, and suggests practical combinations and product‑level enhancements to improve efficiency, accuracy, and usability.
This article explains what AIGC agents are, outlines their four main characteristics, describes the underlying transformer‑based architecture, dual‑stage learning, probabilistic generation and feedback optimization, and explores their current and future commercial use cases across content creation, knowledge bases, customer service, internal operations, and product design.
This article chronicles the development of 1688’s AI buyer assistant “Yuanbao”, detailing why an e‑commerce AI assistant is needed, its functional design, MVP constraints, the shift to a data‑driven 2.0 version, future prospects, and a Q&A, providing practical insights for AI product rollout in B‑to‑C platforms.
This article examines Tencent's large language model deployments across content generation, intelligent customer service, and role‑playing scenarios, detailing the principles and practical implementations of Retrieval‑Augmented Generation (RAG), GraphRAG, and Agent techniques, and discusses challenges, optimization strategies, and real‑world use cases.
This article explores Tencent's large language model deployments across various business scenarios, detailing the principles and practical implementations of Retrieval‑Augmented Generation (RAG), GraphRAG for role‑playing, and Agent technologies, while also covering model fine‑tuning, knowledge‑base construction, and evaluation methods.
The article details Zhihu's technical salon on large‑model engineering, covering the RAG‑based Zhihu Direct Answer system, the open‑source ZhiLight inference framework, prompt engineering, agent research, and future plans for integrating AI into product and community workflows.
This article explains how Java agents work, compares premain and attach agents, shows how to implement entry points, use Instrumentation and Javassist to transform bytecode, provides complete code samples, packaging instructions, and demonstrates the runtime output with diagrams.
This guide explains how Alibaba's open‑source Golang Agent enables full observability for Go applications without modifying source code, covering download, compilation, endpoint configuration, and examples of trace, metric, and log correlation using Docker and OpenTelemetry.
This guide explains how to use Alibaba’s open‑source Golang Agent to automatically instrument Go applications for tracing, metrics, and log correlation without modifying source code, covering binary download, build replacement for go build, endpoint configuration, and step‑by‑step examples with Docker‑based dependencies and Jaeger visualization.
This article explains how to replace invasive manual timing code with a lightweight Java Agent that uses the java.lang.instrument API, ASM bytecode manipulation, and Attach/Arthas tools to automatically measure method execution time and perform dynamic class transformation at runtime.
The article outlines a step‑by‑step methodology for creating Retrieval‑Augmented Generation and custom Agent applications with LangChain, illustrated by an AI assistant for activity components that evolves from a rapid Dify prototype to a LangChain‑based RAG system and finally a hand‑crafted ReAct‑style agent, detailing LCEL chain composition, vector‑search integration, model performance trade‑offs, and a unified routing layer.
This article details Bilibili’s implementation of a large‑language‑model‑driven intelligent assistant for its massive big‑data platform, covering background, problem analysis, architectural design, knowledge‑base construction, precision and recall challenges, deployment across offline and real‑time Spark/Flink diagnostics, and future outlooks.
This article details how PingCAP's three‑person AI Lab leveraged Retrieval‑Augmented Generation (RAG) techniques—including basic RAG, fine‑tuned embeddings, re‑ranking, graph RAG, and agent‑based RAG—to create scalable, multilingual document‑question answering services while addressing large‑scale documentation challenges, model limitations, and user feedback loops.
This article explains how the LangGraph framework combined with Waii’s text‑to‑SQL and visualization capabilities enables conversational data analysis by automatically generating, optimizing, and executing sophisticated SQL queries from natural language inputs.
This article provides a comprehensive overview of large language models (LLMs), covering their basic concepts, relationship with NLP, development history, parameter scaling, offline deployment, practical applications, prompt‑engineering frameworks, retrieval‑augmented generation, LangChain integration, agents, workflow orchestration, and future directions toward multimodal AI and AGI.
Exploring Large Language Models, this article surveys their core concepts, evolution through Transformers, GPT and BERT, generation challenges, diverse applications such as QA, multimodal creation, summarization and retrieval‑augmented generation, prompt‑engineering frameworks and tools, LangChain‑based pipelines, AI‑driven agents, and future prospects toward domain‑specific use, multimodality, and AGI.
This article provides a comprehensive technical overview of JD's self‑built PFinder APM system, detailing its core concepts, multi‑dimensional monitoring capabilities, bytecode‑enhancement mechanisms using ASM, Javassist, ByteBuddy and ByteKit, JVMTI‑based agents, service and plugin loading, trace‑ID propagation across threads, and a prototype hot‑deployment solution.
This article provides a comprehensive technical overview of pfinder, a Java‑based APM system, covering its core concepts, feature set, comparison with other tracing tools, bytecode instrumentation techniques, plugin architecture, trace‑ID propagation across threads, and a simple hot‑deployment implementation.
This article surveys the rapid expansion of large AI models, covering prompt engineering, structured prompts, retrieval‑augmented generation, AI agents, fine‑tuning strategies, vector database technology, knowledge graphs, function calling, and their collective role in moving toward artificial general intelligence.
This article presents Xiaomi's work on LLM‑based Agent technology, covering its perception‑thinking‑action pipeline, technical framework, prompt management, executor and API platform, workflow, optimization strategies, evaluation metrics, and future directions for AI assistants.
This article guides frontend developers through AI development, comparing model training, fine‑tuning, prompt engineering, and Retrieval‑Augmented Generation, then explains agent creation via ReAct and tool‑call methods, and showcases Langchain and Flowise as low‑code frameworks for building domain‑specific AI agents.
The presentation explains how large‑model agents empower AIOps by automating routine tasks, enhancing anomaly detection, fault diagnosis, and remediation, while outlining architectural components, multi‑agent collaboration, and future directions for building self‑healing, observability‑driven operations platforms.
The article examines how LLM‑driven knowledge‑base QA and personal‑assistant agents struggle with context management, token limits, multimodal data, and tool‑parameter parsing, reviews open‑source frameworks such as LangChain, AutoGen and MetaGPT, and argues that fine‑tuning (e.g., LoRA) is essential for domain‑specific, scalable solutions.
Senior algorithm engineer Qi Jianwei from Xiaomi presents a comprehensive overview of building a large‑model‑centric Agent framework for voice assistants, covering prompt design, information retrieval, RAG processes, and future optimization directions to enhance performance and stability.
This article explains how large language models can be extended with LangChain agents using the ReAct reasoning framework to fetch market prices via external tools and automatically calculate a 20% markup for dynamic product pricing, complete with Python code examples.
This guide explains how to set up a Kubernetes pod to act as a Jenkins agent, covering prerequisites, deployment YAML, commands to launch and verify the pod and service, and the Jenkins UI configuration needed to connect the pod as a scalable CI/CD worker.
This article demonstrates how to use LangChain, LLMs, and SerpAPI to create a Weibo influencer‑search tool that extracts UID numbers, scrapes profile data, filters Chinese content, and prepares the information for automated marketing outreach.
Huolala created a visual, drag‑and‑drop LLM application platform that streamlines AI integration, reduces development costs, and enables rapid deployment of agents across marketing, invitation, advertising, and modeling scenarios, boosting efficiency by over 98% while cutting integration time from hours to minutes.
This article examines common Java jar obfuscation tools, identifies their limitations for protecting both proprietary code and third‑party dependencies, and proposes a lightweight Maven‑based encryption combined with a runtime agent that decrypts classes on demand while keeping performance impact under five percent.
This article examines Baidu’s Lingjing developer platform, exploring its origins, design choices, integration of plugins and agents, ecosystem advantages, commercial‑monetization loops, and future roadmap, while providing insights from an interview with platform head Zhang Ruixing on the challenges and opportunities of building AI‑native developer platforms.
This guide walks through installing Jenkins on a Kubernetes cluster using manual YAML manifests, configuring persistent storage, service accounts, ingress, and then demonstrates both static and dynamic Jenkins agents, including pipeline setup, plugin installation, and CI/CD workflow execution.
This article explains how large language models can act as agents by using OpenAI's Function Calling and the ReAct prompting paradigm, compares their trade‑offs, and demonstrates practical implementations with LangChain, including code examples for defining tools, invoking functions, and orchestrating multi‑step reasoning.
This tutorial walks you through installing Zabbix server and agent using Docker Compose, configuring MySQL, setting up automatic agent registration, creating custom dashboards, and optionally integrating LDAP authentication, providing all commands and configuration details for a production‑ready monitoring stack.
Categraf is an all‑in‑one, Go‑based monitoring agent that consolidates metric, log, and trace collection, offering remote_write support, lightweight deployment, and extensive plugin configurations to replace multiple exporters in Prometheus‑based observability stacks.
This article introduces Java Agent technology, explains the differences between premain and agentmain modes, demonstrates how to build, package, and attach agents using Maven and the Attach API, and shows practical bytecode manipulation techniques with Instrumentation and Javassist, complete with code examples.
Prompt‑Ops frameworks like LangChain let developers turn pre‑trained LLMs into versatile applications by abstracting model calls, chaining prompts, integrating tools, managing memory, and handling private data, while addressing challenges such as nondeterminism, version control, and prompt injection in production environments.
This guide explains how to manually create Jenkins JNLP agents on a Kubernetes cluster, covering both static Deployment‑based agents and dynamic agents using the Kubernetes plugin, with detailed YAML definitions, pipeline scripts, and supporting helper functions for a complete CI/CD workflow.
This guide explains how Zabbix agent monitors Linux and Windows systems, compares active and passive modes, and provides detailed optimization tips for OS metrics, CPU, memory, filesystem, Windows services, performance counters, and event logs, including alarm suppression and macro usage.
This guide walks through the complete process of adding a Jenkins agent, from creating the node in the Jenkins UI and installing Java and Git on the remote machine to copying SSH keys, verifying connectivity, and testing the agent’s operation.
This article compares agent‑based and network‑data approaches to cloud‑native application performance monitoring, discussing their architectures, advantages, challenges, and how combining white‑box and black‑box techniques can improve fault detection, scalability, and operational efficiency in complex cloud environments.
This guide explains why a Jenkins agent fails to start with the error "provided port: 8182 is not reachable" and provides step‑by‑step troubleshooting methods such as network testing, Docker port mapping verification, and ensuring proper communication between the agent and master nodes.
This guide explains how to configure Jenkins agent nodes through various methods—including Java Web Start, VM execution, Docker containers, Kubernetes deployments, and SSH—providing step‑by‑step instructions, required code snippets, and tips for successful integration into a CI/CD pipeline.
The article explains that the Jenkins "Launch agent by connecting it to the master" option, formerly called "java web start", lets agents initiate a TCP connection to the server using JNLP, details port configuration, GUI versus headless operation, and alternative launch methods.
This article explains the basics of Java agents, demonstrates how to use premain and agentmain to modify bytecode at load time or during execution, and provides practical examples with ASM to monitor method execution time and capture method parameters and return values in running Java processes.
This guide walks through downloading the pfSense Zabbix template, installing the os‑zabbix‑agent plugin on OPNsense, configuring custom agent parameters, testing connectivity, and setting up the host and template in Zabbix Server to monitor OPNsense metrics.
The article explains why production‑grade Java debugging must avoid stopping the JVM, then details Java‑Agent technology—including JVMTI, startup and runtime loading via the Attach mechanism—and shows how class redefinition and ASM‑based bytecode instrumentation can be combined in a TCP‑server tool to perform online fault isolation without pausing the application.
This article explains Java bytecode fundamentals, its file structure, and demonstrates how to manipulate and enhance bytecode at runtime using ASM, Javassist, the Instrumentation API, JVMTI agents, and the Attach API, providing practical code examples and use‑case scenarios.
This article explains Java bytecode fundamentals, its class‑file layout, constant‑pool details, and then walks through practical bytecode‑enhancement techniques using ASM, Javassist, and the Instrument API to modify and reload classes at runtime for AOP, hot‑deployment and monitoring purposes.
Java dynamic bytecode enhancement uses agents, the Instrumentation API, and the Attach API to modify class bytecode at load time without source changes, enabling non‑intrusive AOP features that power tools such as JRebel for hot deployment, Pinpoint for distributed tracing, Arthas for diagnostics, JVM‑SANDBOX for sandboxed interception, and JRARP for method call recording and playback.
This article explains how the ZhuangZhuang QA team builds and operates a remote device scheduling workflow on the MCP cloud testing platform, detailing the interaction between the automation test platform, MCP, and Agent services, and presenting three practical device allocation strategies for stable, scalable mobile automation.
This article introduces Java instrumentation and the ASM bytecode manipulation library, explains how tools like Jacoco insert probe code on the fly, describes the structure of Java agents, and demonstrates practical bytecode editing methods and use‑cases such as monitoring, hot‑fixing, and mocking.
