BestHub
Sign in
Tagged articles
2074 articles
Page 6 of 21
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 17, 2026 · Artificial Intelligence

Mastering Chunk Splitting for RAG: From Fixed Length to Semantic Segmentation

Chunk splitting, a critical yet often overlooked step in RAG pipelines, dramatically impacts retrieval recall and LLM output quality; this guide walks through three evolution stages—from naive fixed‑length splits to sentence‑aware overlaps and finally semantic, structure‑driven segmentation—complete with code, experiments, and practical pitfalls.

ChunkingLLMRAG
0 likes · 15 min read
Mastering Chunk Splitting for RAG: From Fixed Length to Semantic Segmentation
Tencent Cloud Developer
Tencent Cloud Developer
Mar 17, 2026 · Artificial Intelligence

Why Anthropic Skips Function Calling: Inside the 5 Skill Execution Modes

This article dissects Anthropic's Skill framework, revealing how it drives AI agents through five distinct execution modes—pure prompt injection, script execution, library calls, progressive document loading, and workflow orchestration—while avoiding function‑calling registration and optimizing token usage.

AIAgentFunction Calling
0 likes · 32 min read
Why Anthropic Skips Function Calling: Inside the 5 Skill Execution Modes
Model Perspective
Model Perspective
Mar 16, 2026 · Artificial Intelligence

Can AI‑Generated “Silicon Samples” Replace Real Survey Respondents?

The article explains how large language models can simulate virtual respondents—called silicon samples—to generate synthetic survey data, outlines the four fidelity criteria for evaluating their credibility, and demonstrates practical workflows with the open‑source EDSL Python library.

Artificial IntelligenceEDSLLLM
0 likes · 14 min read
Can AI‑Generated “Silicon Samples” Replace Real Survey Respondents?
Architect's Ambition
Architect's Ambition
Mar 16, 2026 · Artificial Intelligence

Understanding AI Agents: From Chatting to Getting Things Done

The article explains the four essential components of AI Agents—brain, memory, tool, and planning layers—illustrates their implementation with Python code, compares planning strategies, shares a real-world OOM fault‑diagnosis case, and lists common pitfalls to help newcomers build functional agents.

AI AgentLLMPlanning
0 likes · 17 min read
Understanding AI Agents: From Chatting to Getting Things Done
AI Engineer Programming
AI Engineer Programming
Mar 16, 2026 · Artificial Intelligence

Why “Agent Development” Misleads: Framework vs. Harness in LLM Agents

The article explains that the term “Agent development” hides a fundamental split between Agent Frameworks, which give developers building blocks to assemble their own agents, and Agent Harnesses, which provide ready‑to‑run agents, and shows how this distinction affects decisions, maintenance, and troubleshooting.

AI EngineeringAgentClaude Code
0 likes · 10 min read
Why “Agent Development” Misleads: Framework vs. Harness in LLM Agents
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Mar 15, 2026 · Artificial Intelligence

Paper Reading: TiMi – An Inference‑Driven Multi‑Agent System for Quantitative Trading

TiMi is a reasoning‑driven multi‑agent framework that decouples strategy development from minute‑level deployment, leverages LLMs for semantic analysis, code generation and mathematical reasoning, and achieves stable profits, high execution efficiency and strong risk control across more than 200 stock and crypto trading pairs.

Financial AILLMQuantitative Trading
0 likes · 17 min read
Paper Reading: TiMi – An Inference‑Driven Multi‑Agent System for Quantitative Trading
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Mar 15, 2026 · Artificial Intelligence

Is RL Dead in LLM Post-Training? MIT’s RandOpt Challenges Traditional Methods

The MIT‑CSAIL paper introduces RandOpt, a single‑step, gradient‑free, fully parallel post‑training algorithm that adds Gaussian noise to pretrained LLM weights and ensembles the results, achieving or surpassing PPO/GRPO performance by exploiting dense "neural thickets" that emerge as model scale grows.

LLMRandOptScaling Law
0 likes · 12 min read
Is RL Dead in LLM Post-Training? MIT’s RandOpt Challenges Traditional Methods
Woodpecker Software Testing
Woodpecker Software Testing
Mar 15, 2026 · Artificial Intelligence

AI‑Powered Intelligent Regression Testing: Turning Tests into Precise, Real‑Time Defense (2026)

In 2026, intelligent regression testing leverages fine‑tuned LLMs, runtime dependency graphs, and business‑impact weighting to shrink test suites from thousands to dozens, cut execution time by over 90 %, and shift quality from static coverage to real‑time, AI‑driven risk mitigation, while demanding new organizational practices.

AI-driven TestingCIIntelligent Regression Testing
0 likes · 8 min read
AI‑Powered Intelligent Regression Testing: Turning Tests into Precise, Real‑Time Defense (2026)
Fun with Large Models
Fun with Large Models
Mar 15, 2026 · Artificial Intelligence

A Complete Guide to 2026’s Hottest Tech Concept: Agent Engineering

The article explains Agent Engineering—a systematic approach that turns nondeterministic large‑language‑model agents into reliable production‑grade applications through an iterative build‑test‑deploy‑observe‑improve loop, combining product, engineering, and data‑science thinking to address unpredictability and achieve continuous growth.

AI AgentData‑Driven OptimizationIterative Development
0 likes · 12 min read
A Complete Guide to 2026’s Hottest Tech Concept: Agent Engineering
Radish, Keep Going!
Radish, Keep Going!
Mar 15, 2026 · Artificial Intelligence

How Chrome’s WebMCP Lets LLMs Control Browsers Without APIs or Bots

The article examines Chrome 146’s WebMCP standard, showing how declarative and imperative APIs let large language models interact with real browser sessions directly, outperforming prior screenshot‑or‑Playwright tricks in success rate, token cost, speed, and robustness while exposing new challenges for anti‑bot systems.

AI agentsChromeLLM
0 likes · 9 min read
How Chrome’s WebMCP Lets LLMs Control Browsers Without APIs or Bots
PaperAgent
PaperAgent
Mar 15, 2026 · Artificial Intelligence

Why LLM Tool‑Calling Benchmarks Miss Real Users: Introducing WildToolBench

WildToolBench reveals that existing LLM tool‑calling benchmarks overlook real‑world user behavior, and a comprehensive evaluation of 58 models shows even the strongest agents achieve less than 15% session accuracy, highlighting a huge gap between reported performance and practical usability.

BenchmarkLLMagentic AI
0 likes · 10 min read
Why LLM Tool‑Calling Benchmarks Miss Real Users: Introducing WildToolBench
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Mar 13, 2026 · Artificial Intelligence

Why MCP Is Dead and CLI Is Rising: Perplexity’s Shift Sparks Community Support

Although the Model Context Protocol (MCP) was launched by Anthropic in late 2024 and initially praised, users now report severe context‑window costs, instability, and cumbersome authentication, leading Perplexity and others to abandon it in favor of traditional CLI tools that remain more composable and reliable.

AI toolingAgentAnthropic
0 likes · 8 min read
Why MCP Is Dead and CLI Is Rising: Perplexity’s Shift Sparks Community Support
AI Waka
AI Waka
Mar 13, 2026 · Artificial Intelligence

Rethinking LLM Agents: Stream Tool Outputs Directly to the Client

The article critiques the conventional LLM‑agent loop that forces every tool output back through the model, proposes a dual‑output architecture where tools stream multimedia events directly to the client while still returning a compact semantic result to the model, and demonstrates the design with Python code examples.

AgentLLMMultimodal
0 likes · 14 min read
Rethinking LLM Agents: Stream Tool Outputs Directly to the Client
DeepHub IMBA
DeepHub IMBA
Mar 13, 2026 · Artificial Intelligence

Why Bigger Context Windows Make RAG Essential, Not Redundant

Although expanding LLM context windows seems to eliminate the need for Retrieval‑Augmented Generation, in practice larger windows dilute attention and cause retrieval failures, so RAG remains crucial for filtering high‑signal content and maintaining answer quality.

AI ArchitectureAttention DilutionLLM
0 likes · 7 min read
Why Bigger Context Windows Make RAG Essential, Not Redundant
AI Waka
AI Waka
Mar 13, 2026 · Artificial Intelligence

How to Map Enterprise Workflows to Agentic AI Execution Graphs

This article explores the evolution of Agentic AI, outlines a full lifecycle for designing, deploying, and governing AI agents, presents a reference architecture, and demonstrates a practical case study of automating a customer service desk using agentified workflows.

AI ArchitectureEnterprise AutomationLLM
0 likes · 15 min read
How to Map Enterprise Workflows to Agentic AI Execution Graphs
AI Engineer Programming
AI Engineer Programming
Mar 13, 2026 · Artificial Intelligence

Big Model vs. Big Harness: Who Really Powers AI Agents?

The article examines whether the success of AI agents stems from ever‑stronger large language models or from the surrounding harness—context management, tool orchestration, and reliability engineering—by comparing viewpoints, empirical evaluations, and practical guidance for developers.

AI AgentHarness EngineeringLLM
0 likes · 11 min read
Big Model vs. Big Harness: Who Really Powers AI Agents?
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 12, 2026 · Artificial Intelligence

How to Build Cross-Session Memory for RAG Chatbots: Short‑Term vs Long‑Term Strategies

This article explains the role of memory modules in Retrieval‑Augmented Generation systems, compares short‑term and long‑term memory techniques, outlines storage and retrieval methods, discusses management strategies like forgetting and deduplication, and compares LangChain and LlamaIndex implementations for practical deployment.

LLMLangChainLlamaIndex
0 likes · 11 min read
How to Build Cross-Session Memory for RAG Chatbots: Short‑Term vs Long‑Term Strategies
Java Backend Technology
Java Backend Technology
Mar 12, 2026 · Artificial Intelligence

Why a Decade‑Old Java Library Is Jumping Into the AI Race with TOON

The article introduces TOON, a token‑oriented data format that cuts JSON token usage by 30‑60%, and explains how the veteran Java serialization library json‑io has added full TOON support, offering zero‑config, cyclic‑reference handling, and seamless Spring Boot integration for cost‑effective LLM applications.

LLMSpring BootTOON
0 likes · 7 min read
Why a Decade‑Old Java Library Is Jumping Into the AI Race with TOON
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Mar 11, 2026 · Artificial Intelligence

Why LLMs Overthink: ICLR2026 Study Reveals the Key Bottleneck in Inference Efficiency

The ICLR2026 paper identifies reasoning miscalibration—overthinking easy steps and underthinking critical ones—as the root cause of runaway LLM inference costs, and proposes the Budget Allocation Model (BAM) and a training‑free Plan‑and‑Budget framework that smartly distributes compute, achieving up to 70% higher accuracy while cutting token usage by 39% and boosting the new E³ efficiency metric by 193.8%.

Budget Allocation ModelE3 MetricEpistemic Uncertainty
0 likes · 12 min read
Why LLMs Overthink: ICLR2026 Study Reveals the Key Bottleneck in Inference Efficiency
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Mar 11, 2026 · Artificial Intelligence

Paper Review: AlphaBench – Benchmarking LLMs for Formalized Alpha‑Factor Mining

The article reviews AlphaBench, the first benchmark suite for assessing large language models in formalized alpha‑factor mining (FAFM), detailing its three core tasks—factor generation, evaluation, and search—along with experiments on various commercial and open‑source LLMs that reveal strong potential but challenges in robustness, efficiency, and practical usability.

AlphaBenchBenchmarkFAFM
0 likes · 14 min read
Paper Review: AlphaBench – Benchmarking LLMs for Formalized Alpha‑Factor Mining
AI Waka
AI Waka
Mar 11, 2026 · Artificial Intelligence

Why Context Engineering Is the Secret to Smarter AI Agents

The article explains how context engineering—designing the entire information environment for large language models—overcomes prompt engineering limits, mitigates context decay, and improves speed, accuracy, and cost by strategically selecting, compressing, ordering, isolating, and formatting context for production‑grade AI agents.

AI agentsAWS BedrockContext Engineering
0 likes · 24 min read
Why Context Engineering Is the Secret to Smarter AI Agents
macrozheng
macrozheng
Mar 11, 2026 · Backend Development

Why json-io’s New TOON Support Could Cut LLM Token Costs by Up to 60%

The article introduces json-io’s recent addition of full TOON format support—a token‑oriented data notation that removes JSON’s syntactic noise, saving 30‑60% of tokens for LLM APIs, and shows how to integrate it with Java, Maven, and Spring Boot.

LLMSpring BootTOON
0 likes · 7 min read
Why json-io’s New TOON Support Could Cut LLM Token Costs by Up to 60%
Java Backend Technology
Java Backend Technology
Mar 11, 2026 · Artificial Intelligence

Explore The Agency: 55 AI Agent Roles Organized into 9 Departments

The article introduces The Agency, an open‑source collection of 55 specialized AI role definitions grouped into nine functional departments, explains how each Markdown file describes an agent’s identity, mission, workflow and deliverables, and shows two ways to use the agents with Claude Code or as generic prompt templates.

AIAgent RolesClaude
0 likes · 6 min read
Explore The Agency: 55 AI Agent Roles Organized into 9 Departments
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Mar 10, 2026 · Artificial Intelligence

Why the First Token Becomes a Value Garbage Bin – LeCun Team Dissects Spike and Attention Sink Mechanics

The paper by Yann LeCun’s team reveals that massive activation spikes and attention sinks in Transformers are not inherently coupled; spikes arise from position‑0 token interactions and specific feed‑forward dynamics, while attention sinks emerge from Pre‑norm normalization and head dimension, offering practical insights for model quantization and long‑context inference.

Attention SinkLLMMassive Activations
0 likes · 9 min read
Why the First Token Becomes a Value Garbage Bin – LeCun Team Dissects Spike and Attention Sink Mechanics
AI Cyberspace
AI Cyberspace
Mar 10, 2026 · Artificial Intelligence

Mastering Prompt Engineering: Techniques to Guide LLMs Effectively

This article explains the fundamentals of prompt engineering for large language models, covering LLM output configuration, length and sampling controls, various prompt types, chain‑of‑thought and tree‑of‑thought reasoning methods, and practical best‑practice guidelines for creating high‑quality prompts.

AI Prompt DesignLLMOpenAI API
0 likes · 18 min read
Mastering Prompt Engineering: Techniques to Guide LLMs Effectively
PaperAgent
PaperAgent
Mar 10, 2026 · Artificial Intelligence

How MemSifter Delivers High‑Precision, Low‑Cost Long‑Term Memory for LLMs

MemSifter introduces a lightweight agent that outsources memory retrieval for large language models, using a Think‑and‑Rank pipeline and a task‑result‑oriented reinforcement‑learning training paradigm to achieve superior retrieval accuracy and efficiency across eight benchmark tasks while keeping inference overhead minimal.

AgentBenchmarkEfficiency
0 likes · 13 min read
How MemSifter Delivers High‑Precision, Low‑Cost Long‑Term Memory for LLMs
AI Tech Publishing
AI Tech Publishing
Mar 10, 2026 · Artificial Intelligence

Agent Frameworks vs. Agent Harness: Understanding the Key Differences

The article explains how Agent Frameworks and Agent Harness occupy different points on an opinionated spectrum, detailing their abstractions, built‑in components, trade‑offs, and when to choose each, with examples like OpenClaw, LangChain, and Deep Agents.

Agent FrameworkAgent HarnessLLM
0 likes · 5 min read
Agent Frameworks vs. Agent Harness: Understanding the Key Differences
Su San Talks Tech
Su San Talks Tech
Mar 10, 2026 · Artificial Intelligence

Inside Nanobot: A Deep Dive into a Lightweight AI Assistant Framework

This article provides a comprehensive walkthrough of the open‑source Nanobot project, detailing its architecture, core configuration, message bus, tool system, LLM provider, context builder, session management, agent loop, channel integration, cron and heartbeat services, and CLI commands, while illustrating each component with code snippets and diagrams.

AI AssistantLLMNanobot
0 likes · 29 min read
Inside Nanobot: A Deep Dive into a Lightweight AI Assistant Framework
PaperAgent
PaperAgent
Mar 9, 2026 · Artificial Intelligence

How SkillNet Turns AI Agent Experience into Reusable Skills

SkillNet proposes a three‑layer infrastructure that extracts, evaluates, and connects over 200,000 AI‑agent skills into a structured graph, dramatically improving performance across benchmark environments while turning transient agent experience into durable, reusable assets.

AI agentsLLMMachine Learning
0 likes · 6 min read
How SkillNet Turns AI Agent Experience into Reusable Skills
Tencent Technical Engineering
Tencent Technical Engineering
Mar 9, 2026 · Artificial Intelligence

How Does OpenClaw Power Multi‑Agent AI? A Deep Dive into Architecture, Deployment, and Risks

This article explains OpenClaw’s core framework, multi‑agent communication mechanisms, deployment options on cloud or local machines, hardware recommendations, IM tool selection, session and memory management, skill handling, version control, and practical use cases while highlighting important security considerations.

DeploymentLLMOpenClaw
0 likes · 26 min read
How Does OpenClaw Power Multi‑Agent AI? A Deep Dive into Architecture, Deployment, and Risks
Shi's AI Notebook
Shi's AI Notebook
Mar 9, 2026 · Artificial Intelligence

Unpacking the Hype: A Clear Map of LLM, RAG, Agent and Agent Platforms

The article explains why the buzz around AI agents can mislead learners, breaks down overlapping concepts such as LLM, RAG, Tool Use, Agent, Code Agent, and Agent Platform into distinct layers, and outlines a step‑by‑step learning plan to build a solid conceptual map.

AI conceptsAgentAgent Platform
0 likes · 9 min read
Unpacking the Hype: A Clear Map of LLM, RAG, Agent and Agent Platforms
Data STUDIO
Data STUDIO
Mar 9, 2026 · Artificial Intelligence

Boost RAG Accuracy from 60% to 94% with 11 Proven Strategies

This article dissects why naive Retrieval‑Augmented Generation (RAG) often yields only 60% accuracy, then presents eleven concrete ingestion, query, and hybrid techniques—complete with code samples, performance trade‑offs, and real‑world case studies—that together can raise RAG accuracy to 94% while outlining practical implementation roadmaps and common pitfalls.

EmbeddingKnowledge GraphLLM
0 likes · 31 min read
Boost RAG Accuracy from 60% to 94% with 11 Proven Strategies
SuanNi
SuanNi
Mar 9, 2026 · Artificial Intelligence

How Hypernetworks Turn Documents into Instant LLM Skills

This article analyzes the memory and adaptation limits of large language models and presents a hypernetwork‑based approach that instantly converts documents or task descriptions into low‑rank LoRA modules, enabling cheap, on‑demand model updates and cross‑modal knowledge transfer.

AILLMLoRA
0 likes · 9 min read
How Hypernetworks Turn Documents into Instant LLM Skills
DeepHub IMBA
DeepHub IMBA
Mar 8, 2026 · Artificial Intelligence

MIT Study: How Self‑Generated History Pollutes LLM Context and Degrades Multi‑Turn Chats

An MIT paper reveals that storing a language model’s own prior replies—known as context pollution—significantly lengthens the dialogue context while offering little quality benefit, with up to a ten‑fold reduction in tokens and comparable responses for about 70% of turns, especially in open‑source models.

AI agentsLLMMIT study
0 likes · 11 min read
MIT Study: How Self‑Generated History Pollutes LLM Context and Degrades Multi‑Turn Chats
IT Services Circle
IT Services Circle
Mar 8, 2026 · Artificial Intelligence

Mastering LLM Skills: Modular Prompt Engineering for Scalable AI Workflows

The article explains how to replace monolithic prompts with reusable, lazy‑loaded Skill files, compares Skills with Prompt, MCP and Function Calling, shows concrete Skill structures and examples, and demonstrates a Spring Boot AI interview platform with open‑source repositories.

AI workflowFunction CallingLLM
0 likes · 12 min read
Mastering LLM Skills: Modular Prompt Engineering for Scalable AI Workflows
Data Party THU
Data Party THU
Mar 8, 2026 · Artificial Intelligence

6 Practical Context‑Engineering Techniques to Tame RAG Hallucinations

This article explains why retrieval‑augmented generation (RAG) models often hallucinate, introduces the concept of context engineering, and details six practical techniques—including selective retrieval, context compression, hierarchical layout, dynamic query rewriting, memory management, and tool‑aware context—along with their trade‑offs and real‑world impact.

AIContext EngineeringLLM
0 likes · 23 min read
6 Practical Context‑Engineering Techniques to Tame RAG Hallucinations
Fun with Large Models
Fun with Large Models
Mar 8, 2026 · Artificial Intelligence

EasyDataset: End-to-End Guide for Generating QA Datasets for LLM Fine‑Tuning

This article walks through the complete workflow of using EasyDataset to create high‑quality question‑answer pairs for supervised fine‑tuning, covering question generation (single and batch), three generation algorithms, answer generation (including chain‑of‑thought and multi‑turn dialogue), a hybrid quality‑assessment pipeline, and export to Alpaca or ShareGPT formats.

Alpaca formatEasyDatasetKnowledge augmentation
0 likes · 18 min read
EasyDataset: End-to-End Guide for Generating QA Datasets for LLM Fine‑Tuning
AI Explorer
AI Explorer
Mar 8, 2026 · Artificial Intelligence

AutoClip: One‑Click AI Video Highlight Extraction and Editing

AutoClip is an open‑source, locally‑run tool that uses Alibaba's Qwen large language model and OpenAI Whisper to automatically download, transcribe, analyze, and cut high‑light segments from YouTube or Bilibili videos, offering real‑time task monitoring, smart collections, preview, Docker deployment, and a roadmap of future AI‑driven features.

AI video editingDockerFastAPI
0 likes · 7 min read
AutoClip: One‑Click AI Video Highlight Extraction and Editing
Architect
Architect
Mar 7, 2026 · Databases

Why an LLM‑Rewritten SQLite Is 20,000× Slower: Hidden Path Errors and Lessons

A Rust rewrite of SQLite generated largely by an LLM runs a simple primary‑key lookup 20,171 times slower than native SQLite, exposing how seemingly correct code can miss critical system constraints, and illustrating the need for explicit acceptance criteria, benchmark baselines, and governance when using AI‑generated software.

BenchmarkDatabase DesignLLM
0 likes · 19 min read
Why an LLM‑Rewritten SQLite Is 20,000× Slower: Hidden Path Errors and Lessons
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Mar 7, 2026 · Artificial Intelligence

Master Prompt Engineering: Craft Precise Prompts to Unlock LLM Power

This guide breaks down prompt engineering for large language models, explaining why clear, detailed prompts matter, how to define types, avoid ambiguity, use constraints, examples, role‑playing, long‑context techniques, chain‑of‑thought reasoning, and provides ready‑to‑use templates for various scenarios.

AIArtificial IntelligenceChatGPT
0 likes · 88 min read
Master Prompt Engineering: Craft Precise Prompts to Unlock LLM Power
AI Tech Publishing
AI Tech Publishing
Mar 7, 2026 · Artificial Intelligence

A Practical Guide to Evaluating Agent Skills

This article explains why many Agent Skills are released without testing, defines measurable success criteria, and presents a lightweight evaluation framework—including prompt set creation, deterministic checks, optional LLM‑based qualitative checks, and best‑practice recommendations—demonstrated by improving a Gemini Interactions API skill from 66.7% to 100% pass rate.

AI agentsAgent SkillsGemini
0 likes · 13 min read
A Practical Guide to Evaluating Agent Skills
Architecture and Beyond
Architecture and Beyond
Mar 7, 2026 · Artificial Intelligence

Effective Context Transfer in Multi‑Agent Systems: Strategies and Pitfalls

Choosing how to pass context between agents determines system stability, token cost, and debugging difficulty; the article defines context, categorizes four context types, and evaluates four main strategies—shared state, message passing, context compression, and hierarchical routing—detailing mechanisms, use‑cases, implementation pitfalls, and cost‑effectiveness trade‑offs.

LLMSystem Designagent-routing
0 likes · 20 min read
Effective Context Transfer in Multi‑Agent Systems: Strategies and Pitfalls
DaTaobao Tech
DaTaobao Tech
Mar 6, 2026 · Artificial Intelligence

How We Built an LLM‑Powered User Feedback Sentiment Monitoring System

The transaction terminal team created an AI‑driven workflow that automatically collects, cleans, classifies, alerts, distributes, attributes, and reviews user feedback, using a four‑step LLM model to ensure controllable, consistent, and explainable sentiment analysis while boosting efficiency and trust.

AI workflowAutomationLLM
0 likes · 12 min read
How We Built an LLM‑Powered User Feedback Sentiment Monitoring System
Woodpecker Software Testing
Woodpecker Software Testing
Mar 6, 2026 · Artificial Intelligence

How RAG Testing Teams Can Successfully Transform in 2024

With RAG becoming the backbone of enterprise AI, traditional API‑UI testing misses critical semantic errors, leading to high hallucination rates; this article outlines why conventional methods fail and presents a three‑pillar transformation—skill rebuilding, process reengineering, and advanced tooling—backed by real‑world case studies.

AI testingLLMMLOps
0 likes · 9 min read
How RAG Testing Teams Can Successfully Transform in 2024
AI Tech Publishing
AI Tech Publishing
Mar 6, 2026 · Artificial Intelligence

How Codex CLI Compresses Context: Inside the compact() API

The article dissects Codex CLI's two compression paths—local LLM summarization for non‑Codex models and an encrypted compact() API for Codex models—by injecting prompts, extracting system, handoff, and compression prompts, and comparing them with open‑source references to reveal the underlying mechanism.

API analysisCodex CLILLM
0 likes · 5 min read
How Codex CLI Compresses Context: Inside the compact() API
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Mar 5, 2026 · Artificial Intelligence

How a Broken CEO Built an 8‑Agent AI Team in 14 Days and Launched a Site in 24 Hours

After breaking his hip, Cheetah Mobile CEO Fu Sheng used voice commands to train an OpenClaw‑based AI agent called "Sanwan" into an eight‑member team that generated 100k+ reads, millions of views, and a fully functional website in 24 hours, illustrating the power of skill‑driven AI agents over traditional SaaS.

AutomationEasyClawLLM
0 likes · 14 min read
How a Broken CEO Built an 8‑Agent AI Team in 14 Days and Launched a Site in 24 Hours
Mingyi World Elasticsearch
Mingyi World Elasticsearch
Mar 5, 2026 · Artificial Intelligence

Build a Natural‑Language Easysearch Assistant with LLM‑Powered Tool Use (No DSL Required)

This article shows how to create an Easysearch intelligent assistant that lets users manage indexes, write data, search and aggregate documents using Chinese natural language, by combining the DeepSeek large‑language model with OpenAI‑compatible function calling (Tool Use) and a lightweight Node.js executor.

DeepSeekEasysearchLLM
0 likes · 12 min read
Build a Natural‑Language Easysearch Assistant with LLM‑Powered Tool Use (No DSL Required)
Tencent Cloud Developer
Tencent Cloud Developer
Mar 5, 2026 · Artificial Intelligence

20 Cutting‑Edge RAG Optimization Techniques: From Semantic Chunking to Self‑RAG

This article systematically presents twenty practical RAG (Retrieval‑Augmented Generation) optimization methods—covering semantic chunking, chunk‑size evaluation, context‑enhanced retrieval, query transformation, re‑ranking, feedback loops, multimodal and graph RAG, hierarchical retrieval, HyDE, Self‑RAG and reinforcement‑learning‑enhanced RAG—each with clear Python code examples, advantages, limitations and ideal use‑cases.

AILLMRAG
0 likes · 57 min read
20 Cutting‑Edge RAG Optimization Techniques: From Semantic Chunking to Self‑RAG
Kuaishou Tech
Kuaishou Tech
Mar 4, 2026 · Artificial Intelligence

How LLMs Are Revolutionizing Reinforcement Learning for Recommendation Systems

This survey examines the emerging LLM‑RL collaborative recommendation paradigm, outlining its research background, five main collaboration patterns, standardized evaluation protocols, and the key challenges and future directions for building smarter, more robust recommender systems.

Artificial IntelligenceLLMRecommendation Systems
0 likes · 14 min read
How LLMs Are Revolutionizing Reinforcement Learning for Recommendation Systems
Woodpecker Software Testing
Woodpecker Software Testing
Mar 4, 2026 · Artificial Intelligence

Practical Testing of AI Agents: From ChatOps Assistants to Autonomous Driving Bots

The article examines the 2024 shift to dynamic AI agents, outlines why traditional testing falls short, and presents three real‑world case studies—ChatOps IT assistant, multi‑agent e‑commerce risk platform, and embodied inspection robot—detailing novel testing frameworks and measurable improvements.

AI agentsChatOpsHybrid Testing
0 likes · 8 min read
Practical Testing of AI Agents: From ChatOps Assistants to Autonomous Driving Bots
Woodpecker Software Testing
Woodpecker Software Testing
Mar 4, 2026 · Artificial Intelligence

Optimizing Prompt Performance: A Must‑Read Guide for Test Engineers

In the era of LLM‑driven intelligent testing, prompts act as test cases whose latency, token usage, retry rate, context retention, and determinism must be measured and optimized, and this article provides a concrete five‑metric framework and a four‑step practical method backed by real‑world data.

AI testingLLMPrompt Engineering
0 likes · 8 min read
Optimizing Prompt Performance: A Must‑Read Guide for Test Engineers
Tencent Cloud Developer
Tencent Cloud Developer
Mar 4, 2026 · Artificial Intelligence

How OpenClaw Uses a Multi‑Layer Defense System to Prevent LLM Context Overflow

The article provides a detailed technical walkthrough of OpenClaw's three‑stage context‑management framework—including pre‑emptive pruning, LLM‑driven compaction, and overflow‑recovery truncation—showing how each layer protects long‑running AI agent sessions from exceeding token windows while preserving essential information.

Cache OptimizationContext ManagementLLM
0 likes · 27 min read
How OpenClaw Uses a Multi‑Layer Defense System to Prevent LLM Context Overflow
AI Tech Publishing
AI Tech Publishing
Mar 4, 2026 · Artificial Intelligence

AI Agent Context Management: Comparing Six Major Companies' Approaches

The article analyzes how six leading AI‑agent providers—Manus, Cursor, Anthropic, OpenAI, Google, and LangChain—tackle the fundamental problem of when and how a large language model should see information, detailing each solution, a cross‑company comparison matrix, consensus points, controversies, and open research questions.

AI agentsContext ManagementLLM
0 likes · 19 min read
AI Agent Context Management: Comparing Six Major Companies' Approaches
Open Source Tech Hub
Open Source Tech Hub
Mar 4, 2026 · Artificial Intelligence

Building AI Agents: From Basics to OpenAI-Compatible LLM Calls

This article explains the fundamental concepts of AI agents, their perception‑reasoning‑action loop, the evolution from rule‑based bots to LLM‑driven agents, and provides step‑by‑step Python and PHP code for invoking a large language model via the OpenAI‑compatible API.

AILLMOpenAI
0 likes · 11 min read
Building AI Agents: From Basics to OpenAI-Compatible LLM Calls
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Mar 3, 2026 · Artificial Intelligence

Can ROM‑Based LLM Accelerators Reach 20,000 tokens/s and End the GPU Era?

The article analyzes the ROMA and TOM architectures that embed large‑language‑model weights in on‑chip ROM + SRAM, achieving up to 20,000 tokens/s inference speed, compares them with GPU and Taalas solutions, and discusses their impact on edge AI, embodied intelligence, extreme environments, and privacy.

AI acceleratorLLMROM
0 likes · 11 min read
Can ROM‑Based LLM Accelerators Reach 20,000 tokens/s and End the GPU Era?
Tencent Cloud Developer
Tencent Cloud Developer
Mar 3, 2026 · Artificial Intelligence

Why AI Coding Agents Are Just Loops + Context Engineering (And How to Build One)

The article explains that AI coding agents operate as a simple while‑loop driven by context engineering, details their core control flow, compares various tools, and provides a step‑by‑step Python implementation demonstrating how to define tools, system prompts, and the ReAct loop for practical use.

AI codingLLMPython implementation
0 likes · 17 min read
Why AI Coding Agents Are Just Loops + Context Engineering (And How to Build One)
AI Explorer
AI Explorer
Mar 2, 2026 · Operations

Huawei Team’s LLM‑Enhanced Algorithm Wins CVRP Challenge, Redefining Optimization Design

A joint Huawei and City University of Hong Kong team combined large language models with evolutionary computation to solve the capacity‑constrained vehicle routing problem, winning the CVRPLib BKS Global Challenge and demonstrating how AI can automate and transform algorithm design, heralding a new paradigm for operations optimization.

AI for ScienceCVRPEvolutionary Algorithms
0 likes · 7 min read
Huawei Team’s LLM‑Enhanced Algorithm Wins CVRP Challenge, Redefining Optimization Design
Radish, Keep Going!
Radish, Keep Going!
Mar 2, 2026 · Artificial Intelligence

Why Do Your AI Agents Forget Over Time? A 3‑Layer Memory Architecture to Keep Them Sharp

This article explains why AI agents lose recall after prolonged use, analyzes three core flaws in current markdown‑based memory designs, reviews recent research, and presents a deterministic, zero‑cost three‑layer architecture—including short‑term, daily, and long‑term storage, a lightweight knowledge graph, and active forgetting mechanisms—to maintain reliable agent memory.

Knowledge GraphLLMOpenClaw
0 likes · 16 min read
Why Do Your AI Agents Forget Over Time? A 3‑Layer Memory Architecture to Keep Them Sharp
Woodpecker Software Testing
Woodpecker Software Testing
Mar 2, 2026 · Artificial Intelligence

Practical AI Agent Testing: From LLMs to Quality Control Breakthrough

The article recounts a fintech AI advisor project where a four‑layer testing pyramid—intent parsing, planning, tool integration, and end‑to‑end scenarios—was built to overcome the shortcomings of traditional input‑output tests for AI agents, achieving a 76% drop in P0 incidents and a 92.4% task‑completion rate.

AI AgentFinTechLLM
0 likes · 8 min read
Practical AI Agent Testing: From LLMs to Quality Control Breakthrough
Baobao Algorithm Notes
Baobao Algorithm Notes
Mar 2, 2026 · Artificial Intelligence

How “Skills” Turn LLM Prompts into Portable, Engineered Workflows

This article dissects the evolution of LLM prompts into structured, version‑controlled skill packages, explains the AgentSkills specification, details OpenClaw’s implementation, compares prompts, memory, MCP and skills, and provides end‑to‑end examples with code, flowcharts and best‑practice recommendations.

Agent SkillsAutomationLLM
0 likes · 40 min read
How “Skills” Turn LLM Prompts into Portable, Engineered Workflows
PaperAgent
PaperAgent
Mar 1, 2026 · Artificial Intelligence

How On-Policy Context Distillation Enables LLMs to Retain Experience Forever

On-Policy Context Distillation (OPCD) compresses transient in‑context knowledge into LLM parameters, allowing models to permanently retain problem‑solving experience without ground‑truth labels; the article details the OPCD framework, training steps, teacher‑student configurations, and experimental results on math, games, and system‑prompt tasks, highlighting its advantages over traditional context distillation.

Artificial IntelligenceKnowledge DistillationLLM
0 likes · 8 min read
How On-Policy Context Distillation Enables LLMs to Retain Experience Forever
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Feb 28, 2026 · Artificial Intelligence

From Prompt Learning to SIPDO: The Closed‑Loop Evolution Driving Continuous Innovation

The article traces how prompt optimization has mirrored the historical evolution of parameter learning, outlines four development phases—from evolutionary search to beyond‑first‑order methods—and explains how SIPDO’s synthetic‑data feedback and difficulty‑progression create a closed‑loop system that yields consistent performance gains across LLM benchmarks.

AIClosed Loop LearningLLM
0 likes · 18 min read
From Prompt Learning to SIPDO: The Closed‑Loop Evolution Driving Continuous Innovation
AI Explorer
AI Explorer
Feb 28, 2026 · Artificial Intelligence

Explore the Awesome LLM Apps Repository: Hands‑On RAG and AI Agent Examples

The article presents the “Awesome LLM Apps” GitHub repository—over 98 000 stars and hundreds of open‑source LLM projects that showcase Retrieval‑Augmented Generation, AI agents, and multi‑agent collaborations across diverse use‑cases, and offers step‑by‑step guidance on browsing, cloning, configuring, and running these examples for developers, product managers, students, and AI enthusiasts.

AI agentsGitHubLLM
0 likes · 6 min read
Explore the Awesome LLM Apps Repository: Hands‑On RAG and AI Agent Examples
Old Zhang's AI Learning
Old Zhang's AI Learning
Feb 28, 2026 · Artificial Intelligence

How to Build a Private AI‑Powered RSS Reading Knowledge Base

The article details a fully automated workflow that fetches 92 top‑tech blogs via RSS, cleans the content into Markdown, uses a MiniMax‑M2.5 LLM to generate concise Chinese summaries, and delivers them through Bark and a Telegram bot, all stored for seamless integration with Obsidian.

AIAutomationBark
0 likes · 10 min read
How to Build a Private AI‑Powered RSS Reading Knowledge Base
DataFunSummit
DataFunSummit
Feb 27, 2026 · Artificial Intelligence

How Large Language Models Are Revolutionizing Ad Recommendation and Solving Cold‑Start Problems

This article explains how advertising recommendation is evolving from traditional feature‑engineered models to LLM‑driven pipelines, detailing data‑infrastructure challenges, semantic upgrades with multimodal embeddings, case studies in short‑video ads, user cold‑start prompt engineering, and future directions for generative recommendation systems.

Ad TechLLMMultimodal
0 likes · 12 min read
How Large Language Models Are Revolutionizing Ad Recommendation and Solving Cold‑Start Problems
Data Party THU
Data Party THU
Feb 27, 2026 · Artificial Intelligence

How “Vibe Coding” Is Redefining Software Development in 2026

Vibe coding, introduced by Andrej Karpathy, lets developers describe software functionality in natural language, letting large language models generate complete code, and the article reviews its concept, three leading 2026 tools (Cursor, Replit, Windsurf), a step‑by‑step workflow, advantages, drawbacks, and future trends.

AI codingLLMVibe Coding
0 likes · 10 min read
How “Vibe Coding” Is Redefining Software Development in 2026
ByteDance SE Lab
ByteDance SE Lab
Feb 27, 2026 · Artificial Intelligence

How to Build Secure, Scalable LLM Agent Tools: Best Practices & Real-World Cases

This article explains why robust Agent Tools are essential for LLM agents, outlines a five‑stage lifecycle with concrete design principles such as type safety, LLM‑friendly interfaces, OpenAPI integration, self‑healing error handling, human‑in‑the‑loop safeguards, and performance optimizations, and demonstrates their impact through retail and fintech case studies.

Agent toolsIndustry CasesLLM
0 likes · 20 min read
How to Build Secure, Scalable LLM Agent Tools: Best Practices & Real-World Cases
Woodpecker Software Testing
Woodpecker Software Testing
Feb 27, 2026 · Artificial Intelligence

5 Common Mistakes in Testing Retrieval‑Augmented Generation (RAG) Systems

Many teams only verify that a RAG system can answer questions, overlooking retrieval validation, knowledge‑update pipelines, prompt‑retrieval coupling, detailed performance metrics, and hidden security/compliance risks, leading to irrelevant results, hallucinations, latency spikes, and regulatory issues.

ComplianceLLMPrompt Engineering
0 likes · 9 min read
5 Common Mistakes in Testing Retrieval‑Augmented Generation (RAG) Systems
Alibaba Cloud Developer
Alibaba Cloud Developer
Feb 27, 2026 · Information Security

How ABACI AI Agent Automates Linux Kernel Fuzzing, Bug Attribution, and Patch Generation

The article presents ABACI, an AI‑driven kernel defect intelligent agent that automates the entire lifecycle of Linux kernel fuzzing, from test deployment and crash analysis to root‑cause bisect, fix‑bisect, and LLM‑generated patch creation, dramatically reducing manual effort and accelerating vulnerability remediation.

LLMLinuxPatch Generation
0 likes · 23 min read
How ABACI AI Agent Automates Linux Kernel Fuzzing, Bug Attribution, and Patch Generation
AI Tech Publishing
AI Tech Publishing
Feb 27, 2026 · Artificial Intelligence

Step‑by‑Step Guide to Building OpenClaw: A Persistent AI Assistant with Sessions, Tools, and Multi‑Agent Support

This tutorial walks through constructing OpenClaw from scratch, covering persistent JSONL sessions, SOUL.md persona files, tool definitions and an agent loop, permission checks, gateway architecture, context compression, long‑term memory, command queuing, scheduled heartbeats, and multi‑agent routing, all with concrete Python code examples.

AI agentsLLMOpenClaw
0 likes · 38 min read
Step‑by‑Step Guide to Building OpenClaw: A Persistent AI Assistant with Sessions, Tools, and Multi‑Agent Support
Mingyi World Elasticsearch
Mingyi World Elasticsearch
Feb 26, 2026 · Artificial Intelligence

How RAG Gives Large Language Models Their Own Knowledge Base – Illustrated with Easysearch

The article explains why Retrieval‑Augmented Generation (RAG) is needed to overcome large language models' knowledge cut‑off and hallucination issues, details the offline indexing and online retrieval‑generation workflow, compares RAG with fine‑tuning, and shows how Easysearch’s hybrid search makes an effective RAG backbone.

EasysearchHybrid SearchKnowledge Base
0 likes · 10 min read
How RAG Gives Large Language Models Their Own Knowledge Base – Illustrated with Easysearch
Tencent Cloud Developer
Tencent Cloud Developer
Feb 26, 2026 · Artificial Intelligence

Building a Minimalist AI Agent Framework: Theory, Architecture, and Code Walkthrough

This article explains the fundamentals of AI agents, compares major frameworks, introduces the ReAct, Plan‑and‑Execute, and Reflection paradigms, and provides a step‑by‑step Python implementation of a lightweight agent loop with LLM calls, tool execution, and context engineering, complete with usage examples and references.

AI AgentContext EngineeringLLM
0 likes · 28 min read
Building a Minimalist AI Agent Framework: Theory, Architecture, and Code Walkthrough
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Feb 26, 2026 · Artificial Intelligence

Why Longer Token Chains Don't Mean Better Reasoning: Google's Deep Thinking Ratio

Google’s recent study shows that the length of a model’s token chain is negatively correlated with inference accuracy, and introduces the Deep Thinking Ratio (DTR) metric to identify truly reasoning tokens, enabling the Think@n strategy to halve compute cost without sacrificing performance.

Deep Thinking RatioLLMThink@n
0 likes · 6 min read
Why Longer Token Chains Don't Mean Better Reasoning: Google's Deep Thinking Ratio
SuanNi
SuanNi
Feb 25, 2026 · Artificial Intelligence

How SkillsBench Reveals the Real Impact of Agent Skills on LLM Performance

The SkillsBench benchmark systematically evaluates how professionally crafted Skills boost large language model agents across 84 complex tasks, revealing significant performance gains, domain‑specific effects, and the trade‑offs of skill size and model scale.

Agent SkillsBenchmarkLLM
0 likes · 11 min read
How SkillsBench Reveals the Real Impact of Agent Skills on LLM Performance
DataFunSummit
DataFunSummit
Feb 25, 2026 · Artificial Intelligence

Why RAG Fails in Production and How to Fix It: Expert Insights

This article summarizes a DataFun‑hosted roundtable where leading AI experts dissect the gap between RAG’s promise and real‑world deployment, exposing low recall, hallucinations, and cost overruns, then present systematic diagnostics, evaluation metrics, hybrid search, and engineering best practices to reliably operationalize RAG in enterprise settings.

Enterprise AIHybrid SearchLLM
0 likes · 18 min read
Why RAG Fails in Production and How to Fix It: Expert Insights
Data STUDIO
Data STUDIO
Feb 25, 2026 · Artificial Intelligence

Build a Large Language Model from Scratch with PyTorch—No Libraries, No Shortcuts

This guide walks you through building, training, and fine‑tuning a Transformer‑based large language model entirely from scratch using PyTorch, covering tokenization, self‑attention, multi‑head attention, positional encoding, model architecture, data preparation, training loops, and fine‑tuning on custom lyrics.

GPTLLMPyTorch
0 likes · 43 min read
Build a Large Language Model from Scratch with PyTorch—No Libraries, No Shortcuts
AI Insight Log
AI Insight Log
Feb 25, 2026 · Artificial Intelligence

How an Open‑Source Plugin Solves Claude Code’s Session‑Memory Loss

Claude Code forgets all prior context each new session because large language models only see the current window, but the open‑source claude‑mem plugin records project actions, compresses them into semantic summaries, and injects the relevant history back into Claude, dramatically reducing re‑explanation overhead.

AI AssistantClaude CodeLLM
0 likes · 8 min read
How an Open‑Source Plugin Solves Claude Code’s Session‑Memory Loss
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Feb 24, 2026 · Artificial Intelligence

From Traditional RL to LLM‑RL: Theory Derivation and Engineering Improvements

The article walks through the fundamentals of traditional policy‑gradient reinforcement learning, derives the Reinforce objective, maps its concepts to large‑language‑model RL, and then discusses practical engineering solutions such as GRPO, async rollout, importance‑sampling corrections, and token‑flow management for industrial‑scale training.

Async RolloutGRPOImportance Sampling
0 likes · 10 min read
From Traditional RL to LLM‑RL: Theory Derivation and Engineering Improvements
DataFunSummit
DataFunSummit
Feb 24, 2026 · Artificial Intelligence

How Large Language Models Are Redefining Search Ranking at Tencent

This article details Tencent Search's exploration of large‑model‑driven ranking, covering the evolution from traditional keyword retrieval to RAG‑based AI search, the multi‑stage AI ranking architecture (L0‑L5), model training pipelines, distillation, synthetic data generation, and future research directions.

LLMRAGranking architecture
0 likes · 21 min read
How Large Language Models Are Redefining Search Ranking at Tencent
AI Product Manager Community
AI Product Manager Community
Feb 24, 2026 · Artificial Intelligence

Mastering AI Agents: 100 Essential Questions Across 5 Stages

This comprehensive guide walks you through five development stages of AI agents—core concepts, advanced planning, memory management, tool integration, and enterprise deployment—answering 100 practical questions that reveal definitions, architectures, best‑practice patterns, safety measures, and performance‑optimisation techniques for production‑grade agents.

AI agentsAgent ArchitectureEnterprise Deployment
0 likes · 34 min read
Mastering AI Agents: 100 Essential Questions Across 5 Stages
AI Waka
AI Waka
Feb 24, 2026 · Artificial Intelligence

Stop Fragmenting Docs: How Tree‑Based PageIndex Improves RAG Accuracy and Efficiency

The article explains why breaking documents into countless semantic fragments harms retrieval‑augmented generation, introduces PageIndex’s tree‑structured, inference‑driven approach as a superior alternative, and provides detailed setup, usage, and integration instructions for both local and production environments.

AIDocument SearchLLM
0 likes · 9 min read
Stop Fragmenting Docs: How Tree‑Based PageIndex Improves RAG Accuracy and Efficiency
Alibaba Cloud Developer
Alibaba Cloud Developer
Feb 24, 2026 · Artificial Intelligence

Master ReAct Agents: From Observation to Action with Real Code Examples

This article introduces the ReAct agent paradigm—combining reasoning and acting—explains its observation‑think‑act loop, showcases a step‑by‑step weather‑and‑clothing example, outlines essential components, provides pseudo‑code for the execution flow, and links to the Lynxe Func‑Agent framework on GitHub.

AgentLLMReAct
0 likes · 11 min read
Master ReAct Agents: From Observation to Action with Real Code Examples