BestHub
Sign in
Tagged articles
2079 articles
Page 9 of 21
PaperAgent
PaperAgent
Dec 12, 2025 · Artificial Intelligence

How BookRAG Redefines Long-Document Retrieval with Hierarchical Indexing

BookRAG introduces a hierarchical, structure‑aware indexing method that combines tree‑based document representation with graph‑based entity linking and an agent‑driven retrieval pipeline, achieving up to 71.2% recall improvement on multimodal long‑document benchmarks while cutting token usage and latency dramatically.

Agent RetrievalHierarchical IndexingLLM
0 likes · 7 min read
How BookRAG Redefines Long-Document Retrieval with Hierarchical Indexing
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Dec 11, 2025 · Artificial Intelligence

Fine‑Grained Activation Offloading: Cutting Memory Use While Preserving LLM Throughput

The article introduces a fine‑grained activation offloading technique implemented in Megatron‑Core that offloads module‑level activations to CPU, overlaps transfer with computation, and remains compatible with pipeline and virtual pipeline parallelism, dramatically reducing peak GPU memory for large language models while incurring minimal throughput loss.

LLMMegatronMemory Optimization
0 likes · 18 min read
Fine‑Grained Activation Offloading: Cutting Memory Use While Preserving LLM Throughput
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Dec 11, 2025 · Artificial Intelligence

Why Reward Models Need Reasoning: From Scalar Scores to RM‑R1

Interviewers increasingly ask why modern reward models must go beyond scalar scores to incorporate reasoning, and this article explains the limitations of traditional scalar reward models, the benefits of the RM‑R1 framework, and how reasoning‑based rewards improve alignment, stability, and task performance in large language model training.

AI alignmentLLMRLHF
0 likes · 11 min read
Why Reward Models Need Reasoning: From Scalar Scores to RM‑R1
Sohu Tech Products
Sohu Tech Products
Dec 10, 2025 · Artificial Intelligence

Build a Next.js Chatbot Quickly with Vercel AI SDK

This guide explains how to integrate large language models into modern web applications using Vercel AI SDK, covering core modules, package responsibilities, when to choose each package, installation steps, example code for both backend API routes and React front‑end, and a complete quick‑start workflow.

AI IntegrationLLMNext.js
0 likes · 12 min read
Build a Next.js Chatbot Quickly with Vercel AI SDK
Baidu Intelligent Cloud Tech Hub
Baidu Intelligent Cloud Tech Hub
Dec 10, 2025 · Artificial Intelligence

Accelerate LLM Deployment on Baidu Kunlun XPU with the Open‑Source vLLM‑Kunlun Plugin

The vLLM‑Kunlun Plugin, built on the vLLM hardware‑plugin RFC, lets developers deploy any major large language model on Baidu's Kunlun XPU instantly without modifying vLLM core code, dramatically shortening migration time, providing high‑performance fusion operators, and offering open‑source tools for precision verification and profiling.

KunlunLLMOpen Source
0 likes · 8 min read
Accelerate LLM Deployment on Baidu Kunlun XPU with the Open‑Source vLLM‑Kunlun Plugin
BirdNest Tech Talk
BirdNest Tech Talk
Dec 9, 2025 · Artificial Intelligence

How BettaFish Uses Multi‑Agent AI to Break the Information Filter Bubble

BettaFish is a Go‑based, AI‑driven multi‑agent opinion analysis platform that tackles information silos, overload, and bias by aggregating data from diverse sources, iteratively refining results through reflection loops, and delivering visualized, actionable reports for scientific decision‑making.

AIData visualizationGo
0 likes · 24 min read
How BettaFish Uses Multi‑Agent AI to Break the Information Filter Bubble
PaperAgent
PaperAgent
Dec 9, 2025 · Artificial Intelligence

How Code Graph Model (CGM) Redefines Repository‑Level Code Understanding

The Code Graph Model (CGM) introduced by Ant's multimodal code team integrates repository‑level graph structures into open‑source LLMs, achieving a 44% solve rate on SWE‑bench Lite, eliminating agent dependence, and demonstrating a novel graph‑enhanced code model through multi‑granular graph construction, dual‑modal alignment, and a lightweight GraphRAG framework.

AICode GraphGraphRAG
0 likes · 9 min read
How Code Graph Model (CGM) Redefines Repository‑Level Code Understanding
DeWu Technology
DeWu Technology
Dec 8, 2025 · Artificial Intelligence

Unlocking Model Context Protocol (MCP): A Deep Dive into AI‑Database Integration

This article provides a comprehensive technical overview of the Model Context Protocol (MCP), an open‑standard JSON‑RPC 2.0 protocol that enables large language models to securely interact with external data sources, tools, and services, detailing its design, architecture, Python SDK implementation, transport mechanisms, and real‑world deployment examples such as the DW‑DBA‑MCP project.

LLMModel Context ProtocolPython SDK
0 likes · 45 min read
Unlocking Model Context Protocol (MCP): A Deep Dive into AI‑Database Integration
Tencent Technical Engineering
Tencent Technical Engineering
Dec 8, 2025 · Artificial Intelligence

Building Persistent Long‑Term Memory for LLM Agents with LangGraph – A Complete Guide

This article explains how to give large language model agents lasting memory by combining short‑term and long‑term storage in LangGraph, covering concepts, implementation details, database persistence, tool integration, semantic search, memory‑management strategies, checkpoint handling, and a multi‑agent supervisor example.

Agent MemoryLLMLangGraph
0 likes · 43 min read
Building Persistent Long‑Term Memory for LLM Agents with LangGraph – A Complete Guide
Wuming AI
Wuming AI
Dec 7, 2025 · Artificial Intelligence

What Is MCP and How It Revolutionizes AI Tool Integration

This article explains the MCP protocol for AI agents, detailing why a universal tool‑calling standard is needed, how it solves the M×N integration nightmare, the roles and execution stages involved, and demonstrates its use with Cherry Studio while highlighting current limitations.

AI AgentCherry StudioLLM
0 likes · 20 min read
What Is MCP and How It Revolutionizes AI Tool Integration
BirdNest Tech Talk
BirdNest Tech Talk
Dec 7, 2025 · Artificial Intelligence

Recreating DeerFlow’s Multi‑Agent Research Pipeline with LangGraphGo in 30 Minutes

This article walks through the open‑source DeerFlow framework—its multi‑agent architecture, core features, and a step‑by‑step implementation using the Go‑based LangGraphGo library, covering planner, researcher, reporter and podcast nodes, state‑graph design, CLI/web modes, and deployment instructions.

AI researchLLMLangGraphGo
0 likes · 14 min read
Recreating DeerFlow’s Multi‑Agent Research Pipeline with LangGraphGo in 30 Minutes
21CTO
21CTO
Dec 7, 2025 · Backend Development

Top Laravel AI Packages to Power Intelligent Web Apps

This article reviews the most popular and actively maintained Laravel AI packages—including Prism, LarAgent, Laravel AI Toolkit, and Laravel MCP—detailing their features, typical use‑cases, and how to choose the right one for building chatbots, automation agents, content generators, and AI‑enhanced Laravel applications.

AIBackend DevelopmentLLM
0 likes · 6 min read
Top Laravel AI Packages to Power Intelligent Web Apps
PaperAgent
PaperAgent
Dec 7, 2025 · Industry Insights

What 1,000 Trillion Tokens Reveal About the Rise of Open‑Source LLMs

A massive 1 000 trillion‑token study by a16z and OpenRouter shows open‑source models now hold a third of the LLM market, programming tasks have surged to over 50 % of usage, role‑play scenarios dominate open‑source traffic, and price elasticity is surprisingly low, reshaping the competitive landscape.

AI MarketLLMOpen-source models
0 likes · 6 min read
What 1,000 Trillion Tokens Reveal About the Rise of Open‑Source LLMs
Baobao Algorithm Notes
Baobao Algorithm Notes
Dec 7, 2025 · Artificial Intelligence

Can RL Really Boost LLM Reasoning? A Critical Review of Recent Findings

This article critically examines recent RL‑for‑LLM studies, revealing that reinforcement learning improves search efficiency but does not extend the intrinsic reasoning capabilities of base models, and explores the underlying model‑conditioned optimization bias, comparisons with SFT distillation, and the trade‑off with catastrophic forgetting.

Catastrophic ForgettingLLMSFT
0 likes · 11 min read
Can RL Really Boost LLM Reasoning? A Critical Review of Recent Findings
Data Party THU
Data Party THU
Dec 6, 2025 · Artificial Intelligence

Why Adding Toxic Data Can Make Language Models Safer and More Capable

A recent study shows that deliberately mixing a moderate amount of toxic content into large‑language‑model pre‑training actually sharpens the model’s internal representation of toxicity, enabling post‑training interventions to more effectively detoxify the model while preserving or even improving its general capabilities.

LLMToxic Datadetoxification
0 likes · 10 min read
Why Adding Toxic Data Can Make Language Models Safer and More Capable
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Dec 5, 2025 · Artificial Intelligence

Quantitative Finance Paper Summaries (Nov 29–Dec 5 2025)

This article presents concise summaries of five recent AI‑driven finance papers, covering a stress‑testing framework for LLM trading agents, an orchestration framework for financial agents, an event‑reflection memory model for stock forecasting, a hybrid LLM‑Bayesian network architecture for options wheel strategies, and their experimental results.

BenchmarkingFinancial AILLM
0 likes · 12 min read
Quantitative Finance Paper Summaries (Nov 29–Dec 5 2025)
PaperAgent
PaperAgent
Dec 5, 2025 · Artificial Intelligence

Can LLMs Be Trained to Confess? Inside the “Confession” Method for Honest AI

The article reviews OpenAI’s “Confession” training approach for large language models, explains why traditional RLHF fails to ensure honesty, details the confession methodology and PPO update, presents experimental results showing higher honesty rates, analyzes error cases, and discusses limitations and future risks.

AI honestyArtificial IntelligenceConfession Training
0 likes · 6 min read
Can LLMs Be Trained to Confess? Inside the “Confession” Method for Honest AI
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Dec 5, 2025 · Artificial Intelligence

Why Do LLM Function Calls Hallucinate Parameters and How to Prevent It?

This article explains the root causes of hallucinated parameters in LLM Function Calls, outlines five common failure patterns, and presents a systematic five‑step engineering framework—including schema design, prompt rules, dynamic routing, result validation, and clarification—to reliably eliminate such errors in real‑world AI agents.

AI AgentLLMfunction call
0 likes · 11 min read
Why Do LLM Function Calls Hallucinate Parameters and How to Prevent It?
Frontend AI Walk
Frontend AI Walk
Dec 5, 2025 · Artificial Intelligence

Master Prompt Engineering: From Random Chat to Precise Control with Zero-shot, Few-shot, and Chain‑of‑Thought

This article explains how to converse effectively with large language models by mastering three core prompting techniques—Zero‑shot, Few‑shot, and Chain‑of‑Thought—illustrated with front‑end analogies, code snippets, and a step‑by‑step DeepSeek JSON‑generation exercise that shows common pitfalls and best practices.

DeepSeekFew-shotJSON generation
0 likes · 12 min read
Master Prompt Engineering: From Random Chat to Precise Control with Zero-shot, Few-shot, and Chain‑of‑Thought
Fun with Large Models
Fun with Large Models
Dec 5, 2025 · Artificial Intelligence

DeepSeek Math V2 & V3.2: A Plain‑Language Deep Dive into Core Innovations

This article provides a detailed, easy‑to‑understand analysis of DeepSeek‑Math‑V2’s self‑verification training method and DeepSeek‑V3.2’s GRPO framework, sparse‑attention DSA mechanism, massive agent data pipeline, and benchmark results that place both models among the world’s top open‑source large language models.

DeepSeekGRPOLLM
0 likes · 19 min read
DeepSeek Math V2 & V3.2: A Plain‑Language Deep Dive into Core Innovations
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Dec 4, 2025 · Artificial Intelligence

Paper Review: RETuning Boosts Large‑Model Stock Trend Prediction Reasoning

This article analyzes the RETuning framework, which addresses LLMs' bias toward analyst opinions and lack of evidence weighting in stock movement prediction by introducing a two‑stage cold‑start fine‑tuning and reinforcement learning pipeline, evaluating it on the large Fin‑2024 dataset and demonstrating significant F1 gains, inference‑time scaling, and out‑of‑distribution robustness.

Fin-2024GRPOInference Scaling
0 likes · 12 min read
Paper Review: RETuning Boosts Large‑Model Stock Trend Prediction Reasoning
DataFunTalk
DataFunTalk
Dec 4, 2025 · Artificial Intelligence

Agentic RAG, LLM‑Powered Recommendation, and Generative Ranking: Cutting‑Edge AI Search Techniques

This article reviews three advanced AI search solutions—Alibaba Cloud's Agentic RAG architecture for multi‑modal retrieval, Huawei's LLM‑enhanced recommendation system with factorized prompting, and Baidu's generative ranking model GRAB—detailing their technical challenges, design choices, performance gains, and deployment insights.

AI SearchBaiduGenerative Ranking
0 likes · 8 min read
Agentic RAG, LLM‑Powered Recommendation, and Generative Ranking: Cutting‑Edge AI Search Techniques
ShiZhen AI
ShiZhen AI
Dec 4, 2025 · Artificial Intelligence

What Is a Context Window? Explaining LLM Memory Capacity

The article explains that a context window defines an LLM's token‑level memory capacity, shows how longer windows cause quadratic computation growth, introduces KV Cache as a way to extend context without exploding resources, and covers advanced techniques like Ring Attention, NIAH benchmarking, and attention decay in long sequences.

KV CacheLLMNIAH benchmark
0 likes · 6 min read
What Is a Context Window? Explaining LLM Memory Capacity
Aikesheng Open Source Community
Aikesheng Open Source Community
Dec 4, 2025 · Artificial Intelligence

Gemini 3 Pro vs DeepSeek‑V3.2‑Exp: Which LLM Dominates SQL Understanding, Optimization, and Dialect Conversion?

This report evaluates the professional‑grade LLMs Gemini 3 Pro and DeepSeek‑V3.2‑Exp on three SQL‑related dimensions—understanding, optimization, and dialect conversion—using the SCALE benchmark, presenting detailed scores, strengths, weaknesses, and practical recommendations for database engineers and decision makers.

DatabaseDeepSeekGemini
0 likes · 16 min read
Gemini 3 Pro vs DeepSeek‑V3.2‑Exp: Which LLM Dominates SQL Understanding, Optimization, and Dialect Conversion?
Past Memory Big Data
Past Memory Big Data
Dec 4, 2025 · Artificial Intelligence

Text2SQL Showdown: Which Technical Path Delivers Higher Accuracy and Lower Cost?

The article analyzes two contrasting Text2SQL architectures—LLM + RAG + DSL versus rule‑driven NLQ—examining their accuracy under controlled conditions, implementation costs, complex query support, and real‑world suitability for enterprise BI, and concludes which approach is more reliable and cost‑effective.

AI+RulesBusiness IntelligenceDSL
0 likes · 16 min read
Text2SQL Showdown: Which Technical Path Delivers Higher Accuracy and Lower Cost?
Wuming AI
Wuming AI
Dec 3, 2025 · Artificial Intelligence

How to Reduce LLM Hallucinations: Model Selection, Web Search, and Verification Agents

This article explains a step‑by‑step workflow for mitigating large‑language‑model hallucinations by picking low‑hallucination models, leveraging internet‑enabled search tools, rephrasing queries, and creating a dedicated verification assistant with concrete prompts and a Claude implementation.

LLMPrompt Engineeringhallucination
0 likes · 6 min read
How to Reduce LLM Hallucinations: Model Selection, Web Search, and Verification Agents
Tencent Technical Engineering
Tencent Technical Engineering
Dec 3, 2025 · Artificial Intelligence

Why Transformers Power Modern LLMs: A Deep Dive into Architecture and Mechanics

This article provides a comprehensive, step‑by‑step explanation of the Transformer architecture that underpins large language models, covering tokenization, embeddings, positional encoding, attention mechanisms, feed‑forward networks, layer stacking, a detailed translation example, visualized attention weights, and a survey of recent open‑source LLM designs such as DeepSeek V3, OLMo 2, and Gemma 3.

EmbeddingLLMNeural Network
0 likes · 38 min read
Why Transformers Power Modern LLMs: A Deep Dive into Architecture and Mechanics
360 Smart Cloud
360 Smart Cloud
Dec 3, 2025 · Artificial Intelligence

How Model Distillation Enhances LLM Performance on the TLM Platform

This article explains the TLM large‑model development platform and details how knowledge distillation—using soft labels, temperature scaling, and combined loss functions—compresses teacher models into efficient student models, with practical steps and evaluation on the platform.

AIKnowledge DistillationLLM
0 likes · 5 min read
How Model Distillation Enhances LLM Performance on the TLM Platform
AntData
AntData
Dec 3, 2025 · Artificial Intelligence

How to Build and Refine Your Personal AI Agent Assistant

This article walks through turning a generic AI model into a personal assistant by explaining user‑centric workflows, crafting effective natural‑language prompts, adding clarification steps, validating AI‑generated results through multiple methods, and handling errors with product interactions to create a reliable, evolving assistant.

ChatBILLMresult validation
0 likes · 10 min read
How to Build and Refine Your Personal AI Agent Assistant
DataFunTalk
DataFunTalk
Dec 2, 2025 · Artificial Intelligence

How Agentic RAG, LLM‑Powered Recommendation, and Generative Ranking Are Redefining AI Search

This article reviews three cutting‑edge AI search and recommendation techniques—Alibaba Cloud's Agentic RAG architecture, Huawei Noah's LLM‑enhanced recommendation pipeline, and Baidu's GRAB generative ranking model—detailing their design challenges, multi‑modal retrieval strategies, performance gains, and real‑world deployment results.

AI AgentsAI SearchGenerative Ranking
0 likes · 8 min read
How Agentic RAG, LLM‑Powered Recommendation, and Generative Ranking Are Redefining AI Search
AsiaInfo Technology: New Tech Exploration
AsiaInfo Technology: New Tech Exploration
Dec 2, 2025 · Artificial Intelligence

How LLMs Can Revolutionize Test Case Generation: Methods, Benefits, and Challenges

This article examines the shortcomings of manual test case creation, explains how large language models (LLMs) can dramatically improve efficiency, coverage, consistency, and knowledge sharing in software testing, outlines the key capabilities required, and presents a detailed end‑to‑end solution with practical steps, evaluation metrics, and future outlook.

AI automationKnowledge BaseLLM
0 likes · 20 min read
How LLMs Can Revolutionize Test Case Generation: Methods, Benefits, and Challenges
Frontend AI Walk
Frontend AI Walk
Dec 2, 2025 · Artificial Intelligence

Understanding LLMs: A Frontend Developer’s Primer on Large Language Models

The article demystifies large language models for frontend developers by likening token prediction to autocomplete, explaining tokens, context windows, temperature, the two-stage training process, and the critical role of prompts, using concrete code examples and analogies to familiar frontend concepts.

Frontend AnalogyLLMLarge Language Model
0 likes · 10 min read
Understanding LLMs: A Frontend Developer’s Primer on Large Language Models
Tencent Technical Engineering
Tencent Technical Engineering
Dec 1, 2025 · Artificial Intelligence

Do Machines Really Think? Inside Deep Reasoning, Scaling Laws & RLHF for LLMs

This article examines whether large language models truly think, explores the origins of deep reasoning through transformer architectures and scaling laws, reviews chain‑of‑thought and its variants, and analyzes how reinforcement learning from human feedback—including PPO, DPO, and GRPO—helps internalise step‑by‑step reasoning while pointing to future directions such as atomic thought, hierarchical models, and training‑free in‑context knowledge bases.

AI alignmentLLMRLHF
0 likes · 35 min read
Do Machines Really Think? Inside Deep Reasoning, Scaling Laws & RLHF for LLMs
AI Large Model Application Practice
AI Large Model Application Practice
Dec 1, 2025 · Artificial Intelligence

Which Open‑Source Agent Memory Engine Wins? Deep Dive into Mem0, Graphiti & Cognee

This article examines the limitations of LLM short‑term context windows and compares three open‑source long‑term memory frameworks—Mem0, Graphiti, and Cognee—by detailing their architectures, storage modes, integration steps, code examples, strengths, drawbacks, and practical selection guidance for building smarter AI agents.

Agent MemoryGraphitiLLM
0 likes · 20 min read
Which Open‑Source Agent Memory Engine Wins? Deep Dive into Mem0, Graphiti & Cognee
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Nov 30, 2025 · Artificial Intelligence

How TSci Uses LLMs to Automate End‑to‑End Time‑Series Forecasting

The article reviews the TSci framework, an LLM‑driven multi‑agent system that automates data diagnosis, model selection, ensemble forecasting, and report generation for time‑series prediction, achieving up to 38 % lower MAE than LLM baselines and improving report quality across five evaluation dimensions.

Agent FrameworkLLMTSci
0 likes · 10 min read
How TSci Uses LLMs to Automate End‑to‑End Time‑Series Forecasting
DataFunSummit
DataFunSummit
Nov 29, 2025 · Artificial Intelligence

How LLMs Are Transforming Long-Term Cross-Domain Interest Modeling for Recommendations

The Datafun Summit 2025 talk by JD’s algorithm engineer Tian Mingyang explains how generative AI is driving a paradigm shift in recommendation systems, detailing the limits of traditional models, the new dynamic cross‑domain inference chain technique, joint engineering‑algorithm optimizations, and the remaining challenges for future deployment.

AICross-Domain ModelingEngineering Optimization
0 likes · 32 min read
How LLMs Are Transforming Long-Term Cross-Domain Interest Modeling for Recommendations
Data Party THU
Data Party THU
Nov 29, 2025 · Artificial Intelligence

Unlocking AI Agents: From Fundamentals to Building Your First LLM‑Powered Agent

This comprehensive guide explores the concept of AI agents, detailing their definitions, classifications, and core interaction loops, then walks you through building a functional LLM‑driven travel assistant with step‑by‑step code, tool integration, and practical insights on agent versus workflow paradigms.

AI AgentsAgent ArchitectureLLM
0 likes · 39 min read
Unlocking AI Agents: From Fundamentals to Building Your First LLM‑Powered Agent
PaperAgent
PaperAgent
Nov 29, 2025 · Industry Insights

NeurIPS 2025 Insights: AI Agents, Reasoning, and the Shift to Real-World Systems

An analysis of the 5,984 papers accepted at NeurIPS 2025 shows a decisive move from ever‑larger models toward agents, reasoning‑focused LLMs, efficiency engineering, AI for Science, and trustworthy AI, signaling the transition from a research‑toy era to an engineering‑driven AI ecosystem.

AI for ScienceAI trendsLLM
0 likes · 7 min read
NeurIPS 2025 Insights: AI Agents, Reasoning, and the Shift to Real-World Systems
Huya Tech Engineering
Huya Tech Engineering
Nov 28, 2025 · Operations

How LLMs Accelerate Root‑Cause Diagnosis in Large‑Scale Microservices

By abstracting a massive microservice system as a dynamic multi‑layer graph and integrating large language models, the article outlines three evolution stages—from manual expert debugging to rule‑based AIOps and finally LLM‑driven cognitive reasoning—detailing practical workflows, context engineering, and real‑world case studies that dramatically improve MTTR and accuracy.

Context EngineeringLLMObservability
0 likes · 20 min read
How LLMs Accelerate Root‑Cause Diagnosis in Large‑Scale Microservices
Bilibili Tech
Bilibili Tech
Nov 28, 2025 · Artificial Intelligence

How We Built an LLM‑Powered AI Hub to Read and Analyze Community Chats

This article details the design and deployment of a multi‑layer LLM system that automatically reads massive creator group chats, extracts structured insights, mitigates hallucinations with dual‑model verification, uses few‑shot prompting for stable output, and delivers real‑time risk alerts and operational reports.

AI OperationsLLMPrompt Engineering
0 likes · 14 min read
How We Built an LLM‑Powered AI Hub to Read and Analyze Community Chats
ShiZhen AI
ShiZhen AI
Nov 28, 2025 · Artificial Intelligence

DeepSeekMath‑V2 Scores 118/120 on Putnam and Achieves Gold‑Level IMO Performance

DeepSeekMath‑V2, released open‑source on 27 Nov 2025, attains gold‑level results on IMO 2025, scores 118 out of 120 on the Putnam 2024 competition, introduces a generator‑verifier self‑verification architecture, uses GRPO training, and outperforms leading closed‑source models on IMO‑ProofBench.

BenchmarkDeepSeekMath-V2GRPO
0 likes · 7 min read
DeepSeekMath‑V2 Scores 118/120 on Putnam and Achieves Gold‑Level IMO Performance
phodal
phodal
Nov 27, 2025 · Artificial Intelligence

How AutoDev’s Agentic RAG Turns Docs into a Programmable Knowledge Base

This article explains how AutoDev builds an Agentic Retrieval‑Augmented Generation system with a Document Query Language (DocQL) that lets LLM agents navigate hierarchical code and documentation structures using JSONPath‑like queries, detailing implementation, multi‑level keyword expansion, and experimental findings.

AIAgentic RAGDocQL
0 likes · 12 min read
How AutoDev’s Agentic RAG Turns Docs into a Programmable Knowledge Base
Data Party THU
Data Party THU
Nov 27, 2025 · Artificial Intelligence

Choosing an Agent Framework: AutoGen, AgentScope, CAMEL, LangGraph Compared

This article examines the evolution of intelligent agent frameworks, presenting a comprehensive overview of AutoGen, AgentScope, CAMEL, and LangGraph, analyzing their architectures, strengths, limitations, and suitable use cases, and offering guidance on selecting the most appropriate framework for complex multi‑agent applications.

Agent FrameworksLLMcomparative analysis
0 likes · 31 min read
Choosing an Agent Framework: AutoGen, AgentScope, CAMEL, LangGraph Compared
Bilibili Tech
Bilibili Tech
Nov 27, 2025 · Artificial Intelligence

Mastering Agentic Systems with Blades: Concepts, Code, and Workflow Patterns

This article explains what an AI Agent is, distinguishes it from traditional workflows, and demonstrates how to build and customize agents using the Go‑based Blades framework, covering core concepts, code examples, five workflow patterns, best‑practice guidelines, and reference resources.

AIBladesGo
0 likes · 11 min read
Mastering Agentic Systems with Blades: Concepts, Code, and Workflow Patterns
phodal
phodal
Nov 26, 2025 · Artificial Intelligence

How Multi‑Agent AI Transforms Code Review into Automated Fixes

AutoDev leverages a multi‑agent architecture and comprehensive information aggregation to turn traditional, fragmented code review into an intelligent, end‑to‑end process that not only detects issues but also generates and applies corrective patches automatically.

AICode ReviewDevOps
0 likes · 9 min read
How Multi‑Agent AI Transforms Code Review into Automated Fixes
Java Tech Enthusiast
Java Tech Enthusiast
Nov 26, 2025 · Artificial Intelligence

How LLM, RAG, and AI Agents Work Together

The article clarifies how large language models (LLM), retrieval‑augmented generation (RAG), and AI agents complement each other, describing the brain‑like reasoning of LLMs, the dynamic knowledge access provided by RAG, and the autonomous action capabilities of AI agents, plus practical usage scenarios.

AI AgentArtificial IntelligenceLLM
0 likes · 7 min read
How LLM, RAG, and AI Agents Work Together
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Nov 25, 2025 · Artificial Intelligence

FinSentLLM: A Multi‑LLM Framework for Financial Sentiment Prediction

FinSentLLM integrates multiple LLM experts with structured financial semantic signals, achieving 3‑6% higher accuracy and F1 on the Financial PhraseBank compared to baselines, while DCC‑GARCH and Johansen cointegration analyses confirm a statistically significant long‑term co‑movement between the predicted sentiment signals and stock market dynamics.

DCC-GARCHFinSentLLMFinancial Sentiment Analysis
0 likes · 12 min read
FinSentLLM: A Multi‑LLM Framework for Financial Sentiment Prediction
AI Info Trend
AI Info Trend
Nov 25, 2025 · Artificial Intelligence

Why Claude Opus 4.5 Is the New Powerhouse for Enterprise AI Agents

Claude Opus 4.5, Anthropic’s latest flagship LLM, dramatically upgrades reasoning, tool use, and multi‑step automation, targeting high‑intensity enterprise scenarios, offering stronger coding, longer context handling, and better cost‑effectiveness, while still requiring careful prompt engineering and budgeting for token usage.

Claude Opus 4.5Coding AutomationEnterprise AI
0 likes · 7 min read
Why Claude Opus 4.5 Is the New Powerhouse for Enterprise AI Agents
Tencent Technical Engineering
Tencent Technical Engineering
Nov 24, 2025 · Artificial Intelligence

Inside Google gemini-cli: Turning the Terminal into an AI Agent with ReAct Architecture

This article systematically dissects Google’s open‑source gemini‑cli, revealing how it transforms a traditional command‑line terminal into an AI‑driven collaborative interface by detailing its ReAct loop, tool‑calling mechanisms, context management, and extensible architecture for building similar terminal agents.

AI AgentCLIGemini CLI
0 likes · 27 min read
Inside Google gemini-cli: Turning the Terminal into an AI Agent with ReAct Architecture
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Nov 24, 2025 · Artificial Intelligence

Why Dynamic Function Routing Is the Key to Stable LLM Agents

In real‑world LLM agents, giving the model too many tools at once leads to frequent function‑call errors, but applying dynamic function routing to narrow the candidate set dramatically reduces the error rate—from over 20% down to around 1%—and provides clear guidelines on when and how to implement it.

Dynamic RoutingFunction CallingLLM
0 likes · 9 min read
Why Dynamic Function Routing Is the Key to Stable LLM Agents
Architect's Guide
Architect's Guide
Nov 24, 2025 · Artificial Intelligence

Building Java LLM Applications with LangChain4j: A Hands‑On Guide

This tutorial walks through the fundamentals of large language models, prompt engineering, and word embeddings, then shows how to set up a LangChain‑based LLM stack in Java using LangChain4j, covering core modules, memory, retrieval, chains, agents, and complete code examples.

AI AgentsLLMLangChain
0 likes · 15 min read
Building Java LLM Applications with LangChain4j: A Hands‑On Guide
AI Large Model Application Practice
AI Large Model Application Practice
Nov 24, 2025 · Artificial Intelligence

How to Turn Text into an AI‑Powered PPT Video: A Step‑by‑Step Guide

This article breaks down the end‑to‑end engineering pipeline that converts a knowledge source such as a URL or PDF into a narrated PPT‑style video, detailing six core stages—from knowledge extraction and script generation to image creation, voice synthesis, and final video stitching—while highlighting practical model choices, prompt design, and stability tricks.

Artificial IntelligenceLLMPPT
0 likes · 16 min read
How to Turn Text into an AI‑Powered PPT Video: A Step‑by‑Step Guide
AI Tech Publishing
AI Tech Publishing
Nov 23, 2025 · Artificial Intelligence

How Agents Leverage File Systems for Context Engineering

The article examines why file system access is crucial for autonomous agents, outlining common context‑engineering failures such as missing, excessive, or irrelevant information, and demonstrates how using file‑system tools like ls, grep, and write‑file can reduce token waste, enable dynamic storage, improve targeted search, and support continual learning.

Context EngineeringLLMToken Management
0 likes · 11 min read
How Agents Leverage File Systems for Context Engineering
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Nov 21, 2025 · Artificial Intelligence

How to Build a Multi‑Layer Cache for Dynamic RAG Systems

This article explains why dynamic Retrieval‑Augmented Generation (RAG) requires a layered caching strategy rather than simple result caching, details a four‑level cache architecture—including embedding, search, answer, and pipeline caches—provides practical key‑generation and TTL guidelines, and outlines dirty‑data defenses to keep caches consistent and performant.

AI EngineeringCachingLLM
0 likes · 10 min read
How to Build a Multi‑Layer Cache for Dynamic RAG Systems
Youzan Coder
Youzan Coder
Nov 21, 2025 · Artificial Intelligence

How to Build, Evaluate, and Optimize AI Test Agents: A Practical Guide

This guide walks you through creating AI‑powered test agents, defining success metrics, building evaluation datasets, crafting and refining system prompts with techniques like chain‑of‑thought, XML, few‑shot and concise inputs, and scaling the workflow by splitting agents and managing prompt versions.

AI AgentsEvaluationLLM
0 likes · 21 min read
How to Build, Evaluate, and Optimize AI Test Agents: A Practical Guide
Qunhe Technology Quality Tech
Qunhe Technology Quality Tech
Nov 20, 2025 · Artificial Intelligence

How to Build a Quantifiable Quality Assurance System for AI‑Native Products

This article explains the background of AI‑native products, uses VoxDeck as a case study to illustrate typical generation successes and failures, and proposes a systematic, metric‑driven quality‑assurance framework—including data sampling, multi‑dimensional anomaly detection, AI‑assisted checks, and continuous improvement—to boost efficiency, reliability, and business value of AI‑generated content.

AI-nativeLLMPrompt Engineering
0 likes · 14 min read
How to Build a Quantifiable Quality Assurance System for AI‑Native Products
Baobao Algorithm Notes
Baobao Algorithm Notes
Nov 20, 2025 · Artificial Intelligence

Why Reinforcement Learning Preserves LLM Generality Better Than Supervised Fine‑Tuning

The article analyzes why reinforcement learning (RL) fine‑tuning retains a large language model's general abilities better than supervised fine‑tuning (SFT), explaining the off‑policy distribution shift of SFT and the on‑policy data consistency, KL penalty, and trust‑region mechanisms that give RL its anti‑forgetting properties.

Catastrophic ForgettingLLMOn-Policy Data
0 likes · 8 min read
Why Reinforcement Learning Preserves LLM Generality Better Than Supervised Fine‑Tuning
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Nov 19, 2025 · Big Data

How We Migrated 100k BigQuery SQL Scripts to MaxCompute Using AST and LLM Automation

This article details a real‑world migration of a Southeast Asian tech group’s data warehouse from Google BigQuery to Alibaba Cloud MaxCompute, describing the challenges of converting 100,000 SQL scripts, the AST‑driven and LLM‑assisted automation pipeline, rule‑engine iteration, quality control, and the measurable performance and cost benefits achieved.

ASTBigQueryData Warehouse
0 likes · 12 min read
How We Migrated 100k BigQuery SQL Scripts to MaxCompute Using AST and LLM Automation
Baidu Maps Tech Team
Baidu Maps Tech Team
Nov 19, 2025 · Artificial Intelligence

Boosting Socio‑Economic Q&A: The ARAG Framework Merges Structured Data Analysis with RAG

ARAG introduces a novel Retrieval‑Augmented Generation framework that tightly integrates LLM‑driven structured data analysis with unstructured information retrieval, addressing the “structured + unstructured” reasoning gap in socio‑economic queries, and demonstrates superior accuracy, robustness, and hallucination resistance through extensive evaluations.

Data AnalysisHallucination MitigationLLM
0 likes · 12 min read
Boosting Socio‑Economic Q&A: The ARAG Framework Merges Structured Data Analysis with RAG
Data STUDIO
Data STUDIO
Nov 19, 2025 · Artificial Intelligence

Why TOON Beats JSON for LLM Data Exchange: Token Savings and Accuracy Gains

The article explains how the Token‑Oriented Object Notation (TOON) format reduces token usage by 30‑60% and improves accuracy compared to JSON when feeding structured data to large language models, offering concrete syntax, benchmark results, code examples, and guidance on when to adopt it.

BenchmarkJSON alternativeLLM
0 likes · 10 min read
Why TOON Beats JSON for LLM Data Exchange: Token Savings and Accuracy Gains
BirdNest Tech Talk
BirdNest Tech Talk
Nov 18, 2025 · Industry Insights

A Practical Guide to Major LLM Services: URLs, Docs, and API Tips

This article compiles the entry points, documentation links, pricing details, and hands‑on API examples for several leading large‑language‑model providers—including DeepSeek, Alibaba Cloud, Baidu Qianfan, ByteDance Volcengine, OpenRouter, and Google Gemini—while comparing their usability, free‑tier offers, and developer experience.

APICloud AILLM
0 likes · 13 min read
A Practical Guide to Major LLM Services: URLs, Docs, and API Tips
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Nov 18, 2025 · Artificial Intelligence

How to Make LLM Agents’ Function Calls Stable and Accurate: 5 Proven Strategies

This article breaks down why function‑call reliability is the biggest bottleneck for LLM agents and presents a systematic five‑step loop—schema quality, prompt context, sampling, training data, and runtime defenses—plus concrete optimization techniques such as dynamic tool routing, plan‑execute, validation layers, memory injection, and log‑driven tuning, illustrated with real‑world cases.

LLMTool Routingagent
0 likes · 12 min read
How to Make LLM Agents’ Function Calls Stable and Accurate: 5 Proven Strategies
JakartaEE China Community
JakartaEE China Community
Nov 18, 2025 · Artificial Intelligence

How to Build a Retrieval‑Augmented Generation (RAG) System with Langchain4j and Ollama 3

This article explains why Retrieval‑Augmented Generation improves LLM accuracy, outlines the key Langchain4j and Ollama3 components, and provides a step‑by‑step Java example—including Maven setup, document ingestion, embedding, similarity search, prompt creation, and response generation—to demonstrate a functional RAG pipeline.

EmbeddingLLMLangChain4j
0 likes · 8 min read
How to Build a Retrieval‑Augmented Generation (RAG) System with Langchain4j and Ollama 3
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Nov 14, 2025 · Artificial Intelligence

How to Engineer Reliable Function Calls for LLM Agents: An End‑to‑End Framework

This article explains why function‑call accuracy is critical for LLM agents, identifies four common failure causes, and presents a systematic, five‑step engineering framework—including dynamic routing, chain‑of‑thought planning, result validation, memory injection, and log‑driven optimization—backed by concrete examples and quantitative improvements.

Function CallingInterview PreparationLLM
0 likes · 10 min read
How to Engineer Reliable Function Calls for LLM Agents: An End‑to‑End Framework
Programmer DD
Programmer DD
Nov 14, 2025 · Artificial Intelligence

Can TOON Format Cut LLM Token Costs by Up to 60%?

This article explains how the TOON data‑serialization format reduces token usage and improves accuracy for large language model calls compared with traditional JSON, provides benchmark results, outlines scenarios where TOON is advantageous or unsuitable, and shows Java integration examples.

LLMTOONdata serialization
0 likes · 6 min read
Can TOON Format Cut LLM Token Costs by Up to 60%?
AI Tech Publishing
AI Tech Publishing
Nov 13, 2025 · Artificial Intelligence

Claude’s Prompt Engineering Best Practices: A Step‑by‑Step Guide

This guide outlines Claude team’s best practices for prompt engineering, covering core techniques such as clear instructions, background context, specificity, examples, and advanced methods like pre‑filled responses, chain‑of‑thought, output formatting, and prompt chaining, with concrete examples and code snippets.

AI promptingClaudeContext Engineering
0 likes · 18 min read
Claude’s Prompt Engineering Best Practices: A Step‑by‑Step Guide
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Nov 12, 2025 · Artificial Intelligence

Agent Memory Modules Explained: Short‑Term vs Long‑Term Strategies for LLM Agents

This article breaks down the memory systems behind LLM‑based agents, explaining why persistent memory is needed, the differences between short‑term context buffers and long‑term vector stores, practical implementation choices, maintenance strategies, and how to articulate these concepts effectively in technical interviews.

LLMagentretrieval
0 likes · 14 min read
Agent Memory Modules Explained: Short‑Term vs Long‑Term Strategies for LLM Agents
Alibaba Cloud Developer
Alibaba Cloud Developer
Nov 12, 2025 · Artificial Intelligence

How Self‑Programming AI Agents Are Built: From LLM Brain to Dynamic Code Execution

This article explains how a self‑programming AI Agent is constructed by extending large language models as the brain, designing a multi‑area architecture, implementing memory layers, prompt engineering with segment mechanisms, and enabling code generation and execution through a Python‑Java bridge, while sharing practical insights and future directions.

AI AgentCode ExecutionLLM
0 likes · 34 min read
How Self‑Programming AI Agents Are Built: From LLM Brain to Dynamic Code Execution
HyperAI Super Neural
HyperAI Super Neural
Nov 11, 2025 · Artificial Intelligence

How Deepseek-OCR Achieves SOTA Using Ultra‑Low Visual Token Counts

Deepseek-OCR leverages a visual‑compression approach, combining DeepEncoder and the DeepSeek3B‑MoE‑A570M decoder, to represent document text with far fewer visual tokens, achieving up to 97% OCR accuracy and surpassing GOT‑OCR2.0 and MinerU2.0 on OmniDocBench, while the article offers a one‑click deployment tutorial.

DeepEncoderLLMOCR
0 likes · 6 min read
How Deepseek-OCR Achieves SOTA Using Ultra‑Low Visual Token Counts
Old Meng AI Explorer
Old Meng AI Explorer
Nov 10, 2025 · Mobile Development

How Cactus Turns Any Smartphone into a Powerful Offline AI Assistant

Cactus is a lightweight, open‑source mobile AI framework that runs large language models locally on iOS and Android without internet, offering chat, image recognition, and text‑to‑speech while consuming low resources, supporting older phones, and providing simple demo apps and Flutter integration for developers.

AIFlutterLLM
0 likes · 10 min read
How Cactus Turns Any Smartphone into a Powerful Offline AI Assistant
Data Party THU
Data Party THU
Nov 9, 2025 · Artificial Intelligence

Mastering Chunking Strategies for Effective RAG: Fixed, Recursive, Semantic, Structured, and Delayed

This article walks through the core RAG pipeline, explains why chunking is the linchpin of retrieval quality, and provides detailed definitions, trade‑offs, and implementation examples for five chunking techniques—fixed, recursive, semantic, structure‑aware, and delayed—so you can choose the right approach for any document‑heavy AI application.

AIChunkingLLM
0 likes · 10 min read
Mastering Chunking Strategies for Effective RAG: Fixed, Recursive, Semantic, Structured, and Delayed
DataFunSummit
DataFunSummit
Nov 8, 2025 · Artificial Intelligence

How Tencent’s LLM Powers Real‑World AI Solutions with RAG and Agents

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‑playing, while deep‑diving into the RAG, GraphRAG, and Agent technologies that enable smarter, more reliable AI applications.

AILLMRAG
0 likes · 4 min read
How Tencent’s LLM Powers Real‑World AI Solutions with RAG and Agents
AI Product Manager Community
AI Product Manager Community
Nov 8, 2025 · Artificial Intelligence

Why Prompt Engineering Fails: Embracing Context Engineering for Smarter LLMs

The article explains that prompt engineering alone cannot guarantee reliable AI responses because models lack situational awareness, and introduces context engineering as a systematic approach that structures memory, manages context flow, and integrates RAG and evaluation to make large language models truly useful in real‑world applications.

AIContext EngineeringLLM
0 likes · 7 min read
Why Prompt Engineering Fails: Embracing Context Engineering for Smarter LLMs
21CTO
21CTO
Nov 7, 2025 · Artificial Intelligence

any-llm 1.0: Seamlessly Switch Between Cloud and Local LLMs with One Python Library

Mozilla.ai's any-llm v1.0 is an open‑source Python library that unifies access to multiple large language model providers, enabling developers to move between cloud‑based and on‑premise LLMs without rewriting code, while offering async‑first APIs, reusable connections, and extensive compatibility features.

AI developmentLLMPython
0 likes · 4 min read
any-llm 1.0: Seamlessly Switch Between Cloud and Local LLMs with One Python Library
DataFunSummit
DataFunSummit
Nov 7, 2025 · Artificial Intelligence

How Close Are Agents to AGI? Insights from Experiments and Benchmarks

Through a series of experiments, benchmark analyses, and theoretical discussions, this article explores the limits of current AI agents, their underlying mechanisms, performance gaps to human-level intelligence, and the challenges that remain on the path from agents to true AGI.

AGIBenchmarkLLM
0 likes · 26 min read
How Close Are Agents to AGI? Insights from Experiments and Benchmarks
DataFunSummit
DataFunSummit
Nov 7, 2025 · Artificial Intelligence

How Tencent’s LLM Powers Content Creation, Smart Service, and Game NPCs

This article examines Tencent’s large language model deployments across content generation, intelligent customer service, and game role‑playing, and explains the underlying technologies—Supervised Fine‑Tuning, Retrieval‑Augmented Generation, and Agent systems—highlighting how they enhance performance, explainability, and multi‑step reasoning in real‑world business scenarios.

AILLMRAG
0 likes · 4 min read
How Tencent’s LLM Powers Content Creation, Smart Service, and Game NPCs
Ele.me Technology
Ele.me Technology
Nov 7, 2025 · Artificial Intelligence

LLM‑SM Hybrid Strategies: Boosting Decision Optimization and Store Design

Recent advances in large language models (LLMs) have sparked interest in their decision‑making capabilities, yet challenges remain; this article explores classic prediction‑optimization pipelines, introduces emerging LLM‑as‑Predictor/Ranker/Optimizer paradigms, and details practical case studies on delivery‑price optimization and intelligent store‑decoration recommendation using LLM‑SM hybrid systems.

Decision OptimizationHybrid ModelingLLM
0 likes · 30 min read
LLM‑SM Hybrid Strategies: Boosting Decision Optimization and Store Design
JD Tech
JD Tech
Nov 6, 2025 · Artificial Intelligence

LLMs Revolutionize Recommendation Systems: From Generative Models to Production

This article surveys the evolution of generative recommendation systems powered by large language models, detailing their technical foundations, engineering challenges, recent breakthroughs, and future research directions, while highlighting why the paradigm shift is occurring now.

AI EngineeringGenerative RecommendationLLM
0 likes · 30 min read
LLMs Revolutionize Recommendation Systems: From Generative Models to Production
Tencent Cloud Developer
Tencent Cloud Developer
Nov 6, 2025 · Artificial Intelligence

From Prompt to Multi‑Agent: How LLMs Evolve into Autonomous Agents

Since ChatGPT's debut, the LLM landscape has progressed through four stages—prompt engineering, chain orchestration, autonomous agents, and multi‑agent systems—each enhancing intelligence and automation, with this article detailing their evolution, advantages, drawbacks, and practical implementation examples in Go.

GoLLMagent
0 likes · 24 min read
From Prompt to Multi‑Agent: How LLMs Evolve into Autonomous Agents
AI Tech Publishing
AI Tech Publishing
Nov 5, 2025 · Artificial Intelligence

Why AI Agents Should Be Positioned as Assistants, Not Replacements

The article explains that marketing AI agents as human replacements leads to poor performance, professional resistance, and hallucination risks, and argues that repositioning them as assistants with human‑in‑the‑loop verification improves efficiency and acceptance.

AI AgentBI EngineerData Agent
0 likes · 3 min read
Why AI Agents Should Be Positioned as Assistants, Not Replacements
Kuaishou Tech
Kuaishou Tech
Nov 5, 2025 · Artificial Intelligence

How HiPO Gives LLMs a Smart Thinking Switch to Cut Costs and Boost Accuracy

This article explains the overthinking problem of large language models, introduces the HiPO framework with hybrid data cold‑start and reinforcement‑learning reward mechanisms that let models decide when to think deeply or answer directly, and shows experimental results demonstrating significant efficiency gains and accuracy improvements across multiple benchmarks.

EfficiencyHybrid Policy OptimizationLLM
0 likes · 13 min read
How HiPO Gives LLMs a Smart Thinking Switch to Cut Costs and Boost Accuracy
Data Party THU
Data Party THU
Nov 5, 2025 · Artificial Intelligence

How to Give LLM Agents Memory, Reflection, and Goal Tracking

This article explains why current LLM agents lose context after each conversation and presents a practical architecture—using SQLite for structured storage, a vector database for semantic retrieval, and LLM‑driven reflection—to add persistent memory, self‑evaluation, and goal‑tracking capabilities that turn agents into learning partners.

Goal TrackingLLMMemory
0 likes · 10 min read
How to Give LLM Agents Memory, Reflection, and Goal Tracking
Code Mala Tang
Code Mala Tang
Nov 5, 2025 · Backend Development

How to Build a Production-Ready Async LLM API with FastAPI

Learn how to design and deploy a high‑performance, production‑grade LLM API using FastAPI, covering async routing, type‑safe Pydantic models, streaming via SSE/WebSockets, middleware, caching, rate limiting, observability, retries, and cost‑control strategies for robust AI services.

AsyncFastAPILLM
0 likes · 12 min read
How to Build a Production-Ready Async LLM API with FastAPI
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Nov 5, 2025 · Artificial Intelligence

Why Production-Ready RAG Is Ten Times Harder Than a Simple Demo

Building a Retrieval‑Augmented Generation (RAG) system may be straightforward in code, but making it reliable, accurate, and scalable in production involves challenges across data preparation, vector retrieval, query rewriting, generation control, and system integration, turning a demo into a truly useful AI service.

AILLMPrompt Engineering
0 likes · 8 min read
Why Production-Ready RAG Is Ten Times Harder Than a Simple Demo
JavaGuide
JavaGuide
Nov 5, 2025 · Artificial Intelligence

Cursor Goes Beyond the IDE with Agent Mode and Its Own Composer LLM

Cursor, once hailed as the leading AI‑enhanced IDE, has shifted its focus by making Agent mode the default and launching its own large‑model Composer, which the vendor claims runs four times faster than comparable models, though real‑world performance remains to be validated.

AI IDEClaudeCodex
0 likes · 4 min read
Cursor Goes Beyond the IDE with Agent Mode and Its Own Composer LLM
AI2ML AI to Machine Learning
AI2ML AI to Machine Learning
Nov 4, 2025 · Artificial Intelligence

Common Debugging Signals for Large Language Models

This article outlines the end‑to‑end workflow for large‑model training, highlights typical debugging challenges such as memory OOM, performance bottlenecks, and gradient issues, and provides concrete strategies, tools (DeepSpeed, Megatron, Torchtitan, veScale) and best‑practice checklists to help engineers diagnose and resolve problems efficiently.

DebuggingDeepSpeedLLM
0 likes · 12 min read
Common Debugging Signals for Large Language Models
DataFunTalk
DataFunTalk
Nov 4, 2025 · Artificial Intelligence

Can LLMs Trade Crypto Profitably? Inside the Alpha Arena Competition

Alpha Arena’s first season pitted six leading large language models against real crypto markets with $10,000 each, revealing stark differences in trading bias, risk management, and sensitivity to prompts, as Qwen3‑Max and DeepSeek outperformed GPT‑5, while detailed case studies expose model vulnerabilities and future research directions.

AI AgentsAlpha ArenaLLM
0 likes · 12 min read
Can LLMs Trade Crypto Profitably? Inside the Alpha Arena Competition
Data STUDIO
Data STUDIO
Nov 4, 2025 · Artificial Intelligence

How to Build a Memory-Enabled AI Agent with SQLite and Vector Search

This article explains how to give AI agents persistent memory, reflection, and goal‑tracking by storing interaction summaries in SQLite, embedding them for semantic retrieval with a vector database, and using LLM‑generated prompts to recall, reflect, and manage objectives across sessions.

AI AgentGoal TrackingLLM
0 likes · 10 min read
How to Build a Memory-Enabled AI Agent with SQLite and Vector Search
dbaplus Community
dbaplus Community
Nov 3, 2025 · Artificial Intelligence

How RAG Turns Natural Language Queries into Accurate SQL for Data Platforms

This article explains how Retrieval‑Augmented Generation (RAG) combines vector databases with large language models to let non‑technical users ask natural‑language questions and receive precise SQL statements, detailing the workflow, architecture, chunking methods, performance gains, and remaining challenges.

Data PlatformLLMRAG
0 likes · 17 min read
How RAG Turns Natural Language Queries into Accurate SQL for Data Platforms
DataFunSummit
DataFunSummit
Nov 3, 2025 · Artificial Intelligence

How Tencent’s LLM Powers Real‑World AI: From RAG to Agents

This article examines Tencent's large language model applications across diverse business scenarios, detailing core use cases such as content generation, intelligent customer service, and role‑playing, and explains the three key technologies—Supervised Fine‑Tuning, Retrieval‑Augmented Generation, and Agents—that enable these capabilities.

AI applicationsLLMRAG
0 likes · 4 min read
How Tencent’s LLM Powers Real‑World AI: From RAG to Agents
Meituan Technology Team
Meituan Technology Team
Nov 3, 2025 · Artificial Intelligence

Introducing VitaBench: A Real-World Agent Benchmark That Reveals a 30% Success Gap

VitaBench, a new open‑source benchmark from Meituan’s LongCat team, evaluates LLM‑driven agents across three realistic life‑service scenarios—food ordering, restaurant dining, and travel planning—using 66 tools and quantifying reasoning, tool, and interaction complexities, exposing a mere 30% success rate on complex cross‑scene tasks.

AIBenchmarkInteraction
0 likes · 14 min read
Introducing VitaBench: A Real-World Agent Benchmark That Reveals a 30% Success Gap