Author

Wu Shixiong's Large Model Academy

We continuously share large‑model know‑how, helping you master core skills—LLM, RAG, fine‑tuning, deployment—from zero to job offer, tailored for career‑switchers, autumn recruiters, and those seeking stable large‑model positions.

111

Articles

Likes

241

Views

Comments

Latest from Wu Shixiong's Large Model Academy

100 recent articles max

Wu Shixiong's Large Model Academy

Apr 20, 2026 · Artificial Intelligence

How to Build Multi‑Step Reasoning Training Data for Deep Research Agents

Standard QA datasets fall short for deep research tasks because they lack the multi‑step, dynamic reasoning required; this article explains why, outlines four data‑construction techniques—SailorFog‑QA, WebFrontier, WebShaper, E2HQA—details trajectory sampling, filtering, scale considerations, and interview‑ready explanations.

AI agentsLLM trainingMulti-step Reasoning

0 likes · 16 min read

How to Build Multi‑Step Reasoning Training Data for Deep Research Agents

Wu Shixiong's Large Model Academy

Apr 17, 2026 · Backend Development

How Claude Code’s Memory System Works: From SHA‑256 Storage to Coalescing Extraction

This article dissects Claude Code’s Memory subsystem, explaining the distinction between Session logs and persistent Memory, the SHA‑256‑based storage layout, file indexing, four memory types, prompt injection steps, two write pathways, the ExtractionCoordinator’s coalescing strategy, and how to explain the design in interviews.

Claude CodeConcurrencyPrompt Engineering

0 likes · 19 min read

How Claude Code’s Memory System Works: From SHA‑256 Storage to Coalescing Extraction

Wu Shixiong's Large Model Academy

Apr 16, 2026 · Interview Experience

Turn Memorized Answers into Deep Understanding for Tech Interviews

This article explains why interviewers use seemingly rote questions to probe a candidate's true grasp of concepts, contrasts memorization with genuine understanding using PPO vs GRPO, and provides a practical three‑question framework and dialogue examples to help candidates answer technical principle questions confidently.

Answering TechniquesGRPOPPO

0 likes · 12 min read

Turn Memorized Answers into Deep Understanding for Tech Interviews

Wu Shixiong's Large Model Academy

Apr 15, 2026 · Interview Experience

How to Turn Your RAG Project into a Compelling Interview Story

This article explains why many candidates fail to convey their RAG projects in interviews, contrasts tool‑list versus problem‑driven presentations, and provides a four‑question framework with concrete metrics, decision‑making examples, and actionable steps to rebuild a persuasive project narrative.

AIDecisionMakingLLM

0 likes · 16 min read

How to Turn Your RAG Project into a Compelling Interview Story

Wu Shixiong's Large Model Academy

Apr 14, 2026 · Artificial Intelligence

Designing High‑Quality Tools for Deep Research Agents: From Search to Python Execution

This article explains how to turn simple API calls into robust, noise‑filtering tools—Search, Visit, Scholar, and Python—by adding domain blacklists, relevance scoring, query‑driven extraction, safety sandboxes, and a unified registry, ultimately boosting the success rate of LLM‑driven research agents.

AI agentsLLM safetyReact

0 likes · 32 min read

Designing High‑Quality Tools for Deep Research Agents: From Search to Python Execution

Wu Shixiong's Large Model Academy

Apr 13, 2026 · Artificial Intelligence

Turning ReAct from Demo to Production: Handling Failures, Loops, and Token Budgets

This article explains how to upgrade a ReAct agent from a proof‑of‑concept to a production‑ready system by classifying tool failures, detecting repeated search loops, managing token budgets, and adding structured logging, complete with Python implementations and practical interview guidance.

Agent EngineeringLLMLoop Detection

0 likes · 24 min read

Turning ReAct from Demo to Production: Handling Failures, Loops, and Token Budgets

Wu Shixiong's Large Model Academy

Apr 10, 2026 · Artificial Intelligence

How to Build a Robust Agent Memory System: Architecture, Management, and Evaluation

This article provides a comprehensive guide to designing, implementing, and evaluating an Agent Memory module for large‑language‑model assistants, covering memory types, short‑ and long‑term storage, conflict resolution, hybrid retrieval, compliance, and practical interview answers.

Agent MemoryComplianceHybrid retrieval

0 likes · 32 min read

How to Build a Robust Agent Memory System: Architecture, Management, and Evaluation

Wu Shixiong's Large Model Academy

Apr 9, 2026 · Artificial Intelligence

How to Jump‑Start a RAG System Without Any Labeled Data

Building a Retrieval‑Augmented Generation (RAG) system from scratch without existing QA pairs requires a systematic cold‑start approach that creates synthetic QA data, establishes baseline metrics, iteratively improves via expert labeling and real user feedback, and ensures document quality for reliable evaluation.

AnnotationLLMRAG

0 likes · 17 min read

How to Jump‑Start a RAG System Without Any Labeled Data

Wu Shixiong's Large Model Academy

Apr 8, 2026 · Artificial Intelligence

From RAG to Deep Research Agent: Building a Multi‑Round AI Agent with ReAct

This article walks through the practical differences between simple Retrieval‑Augmented Generation and a full Deep Research Agent, explains the four pillars that support such agents, demonstrates a minimal ReAct implementation with robust error handling, and shares interview tips for showcasing these systems.

LLMPrompt EngineeringRAG

0 likes · 18 min read

From RAG to Deep Research Agent: Building a Multi‑Round AI Agent with ReAct

Wu Shixiong's Large Model Academy

Apr 7, 2026 · Artificial Intelligence

Why Hybrid Retrieval Beats Pure Vector Search: BM25, RRF, and Real‑World Experiments

This article dissects the shortcomings of pure vector retrieval, explains how BM25 complements it, compares weighted‑sum and Reciprocal Rank Fusion (RRF) strategies, shows experimental results that identify optimal weight and k values, and provides practical engineering tips for deploying hybrid search in RAG systems.

BM25Hybrid retrievalRAG Systems

0 likes · 24 min read