Master's graduate from Beijing Institute of Technology, published four top‑journal papers, previously worked as a developer at ByteDance and Alibaba. Currently researching large models at a major state‑owned enterprise. Committed to sharing concise, practical AI large‑model development experience, believing that AI large models will become as essential as PCs in the future. Let's start experimenting now!
This article walks through LangChain DeepAgents' Tool Selector and Todo List middleware, detailing why they are needed, how they streamline tool usage and task planning, and provides step‑by‑step Python examples that demonstrate improved performance on complex multi‑tool tasks.
This guide walks readers through installing EasyDataset, creating a project, uploading documents, choosing appropriate chunking strategies, cleaning the data, generating domain tag trees, and exporting a polished pre‑training dataset, with concrete examples, configuration screenshots, and practical recommendations for each step.
This article explains how LangChain DeepAgents' Summarization middleware automatically compresses conversation history to overcome large‑model context window limits, detailing its core mechanism, applicable scenarios, configuration parameters (trigger, keep, model, summary_prompt), and step‑by‑step Python examples that illustrate its integration and internal message flow.
This article introduces LangChain's DeepAgents framework, explains its design goals, compares it with LangChain and LangGraph, and provides a step‑by‑step code walkthrough that demonstrates task planning, sub‑agent delegation, tool usage, and result generation for building complex AI agents with just a few lines of code.
Qwen3.5‑397B‑A17B, the newly open‑sourced multimodal giant, combines a 400‑billion‑parameter sparse MoE architecture with FP8 pipelines and an asynchronous RL framework to deliver GPT‑5.2‑level capabilities, 60% lower memory usage, up to 19× higher throughput, and extensive image, video, and agent support, while outlining its deployment requirements and API pricing.
The article presents a step‑by‑step design and implementation of a Claude‑style Skills mechanism for LangChain agents, using a double‑layer tool architecture, state‑driven dynamic filtering, and middleware interception to load only relevant tools, dramatically reducing token consumption and improving decision quality and response speed.
The article provides a detailed technical comparison of Anthropic's Claude Opus 4.6 and OpenAI's GPT‑5.3 CodeX, covering performance gains, context window size, agent teamwork, programming benchmarks, new features such as adaptive thinking and interactive development, and offers guidance on choosing the right model for specific workflows.
OpenClaw, a 2026 open‑source AI agent, combines a protocol‑agnostic gateway, a four‑layer memory system, and an extensible Agent Skills framework to enable real‑time cross‑platform interaction, long‑term learning, and seamless integration with Chinese large language models and popular chat applications.
This article explains the three‑layer Agent Skills architecture, demonstrates step‑by‑step creation and configuration of a Skill using Claude Code—including metadata, instruction, and resource layers, advanced scripting integration, and a detailed comparison with MCP, highlighting token savings and use‑case differences.
This tutorial explains the OpenAI‑style request and response schema, demonstrates low‑level API calls with the requests library, compares them to the high‑level openai package, and walks through building a streaming multi‑turn chatbot that interacts with a locally hosted large language model.
