Tagged articles
Prompt Optimization
33 articles · Page 1 of 1
A survey from CAS, Meituan, and partners introduces a unified framework for Recursive Self-Improvement (RSI) in LLM agents, organizing 40 studies around three core questions — when to update, where to modify, and how to validate — and a seven-step lifecycle that turns raw experience into verified, reusable components across Prompt, Memory, Skill, and Harness layers.
Agent LifecycleExperience-Driven LearningHarness Evolution
0 likes · 17 min read

This article details a production-ready GEPA (Genetic-Pareto Reflective Prompt Evolution) system that automates prompt optimization through a data-driven loop of inference, scoring, reflection, and Pareto-frontier selection, replacing manual trial-and-error with a task-agnostic, zero-configuration pipeline that supports classification, scoring, and clustering tasks while preserving explainability.
DSPyGEPALLM Judge
0 likes · 31 min read

Google released two Agent Skill papers—WikiSkill and SKILL.state—introducing a structured knowledge layer for skill evolution and a state‑machine execution model that dramatically reduces prompt length, improves accuracy, and demonstrates strong cross‑model transfer and robustness across a suite of benchmarks.
Agent SkillLLMLong-Horizon Agents
0 likes · 13 min read

This article walks through the complete process of creating a DeepSeek Harness (DSH) plugin that adds an "AI Optimize" button to the chat UI, explains the DSH architecture, shows how to develop, test, package, publish to npm, and install the plugin, and provides concrete code snippets and request/response examples.
AI AgentDSH PluginDeepSeek Harness
0 likes · 15 min read

The article explains that attaching too many skills to coding agents like Codex or Claude Code incurs context, decision, and misdirection costs, and proposes three principles for skill selection, clear trigger definitions, and regular audits, plus a maintenance workflow using Git, regression testing, and a deletion culture.
AI ProductivityGit version controlPrompt Optimization
0 likes · 5 min read

The article dissects the open‑source hermes‑agent‑self‑evolution repository, explaining how DSPy leverages large‑model APIs to diagnose skill failures and rewrite SKILL.md, while GEPA orchestrates mutation, evaluation, and Pareto‑based selection to iteratively improve Hermes Agent skills offline.
AI agentsDSPyGEPA
0 likes · 11 min read

Prompt engineering optimizes LLM interactions by designing clear system and user prompts, structuring examples, and employing techniques such as few‑shot learning, chain‑of‑thought, HyDE, ReAct, and automated optimizers, which together improve accuracy, consistency, efficiency, and token cost.
Few-Shot LearningLLM InteractionPrompt Optimization
0 likes · 20 min read


TonyBaiJul 3, 2026 · Artificial Intelligence
The article presents twenty essential loop design patterns for industrial AI systems, explains how they differ from single‑call prompts, provides concrete examples, code snippets, and use‑case scenarios, and shows how these loops enable self‑improvement, memory, planning, exploration, and system optimization for AI agents.
AIAgentLoop Engineering
0 likes · 23 min read

The article explains how overly long prompts dilute a large‑model’s attention, causing slower responses and contradictory outputs, and introduces a three‑step prompt‑decay audit—density measurement, slimming, and versioned output—that cuts response time from 1.8 s to 0.6 s, triples logical density, and reduces hallucinations by 60 %.
LLMPrompt OptimizationPrompt engineering
0 likes · 6 min read

The article details a systematic practice—starting from the “iceberg” challenges of finance, through data and knowledge engineering, reverse knowledge extraction with REER, multi‑dimensional synthetic data generation, prompt engineering (APO), cost‑aware fine‑tuning, inference acceleration, and emotion‑value evaluation—culminating in actionable guidelines for deploying large models in banking scenarios.
Knowledge EngineeringPrompt Optimizationemotion evaluation
0 likes · 14 min read

The article breaks down token billing, shows that input tokens account for 70‑90% of cost, and provides concrete techniques—file filtering, context compression, doc‑driven prompts, memory caching, plan mode, output trimming, and model switching—across Claude Code, Codex, and OpenCode, culminating in a 10‑step checklist and a comparison table that demonstrate up to 80% token savings.
AI codingClaude CodeCodex
0 likes · 11 min read

SkillOpt treats an agent's skill file as a trainable text document, iteratively editing it with a frozen LLM to boost performance on tasks with known correct answers, achieving large benchmark gains without fine‑tuning model weights while remaining portable and auditable.
AI agentsLLM training alternativePrompt Optimization
0 likes · 18 min read

This article explains why structured prompts are essential for AI agents, outlines their six core components, compares major frameworks such as R‑C‑S‑W‑O, Zeng Yingjie three‑stage and CRISPE, offers five optimization techniques, and provides detailed case studies on building personal prompt libraries and enterprise‑level IT policy assistants.
AI agentsCRISPECoze platform
0 likes · 35 min read

The HiLight approach inserts lightweight highlight tags into full-length inputs, training a small Emphasis Actor to score token importance and guide a frozen large language model, improving performance on tasks like recommendation and QA without modifying the solver, while keeping low latency and training cost.
HighlightingLLMPrompt Optimization
0 likes · 9 min read


AI WakaApr 26, 2026 · Artificial Intelligence
The article examines how Google’s Agent Development Kit (ADK) tackles the context‑window bottleneck by introducing a three‑layer Skills architecture that lets agents load domain‑specific knowledge on demand, compares implementation modes, provides a step‑by‑step weather‑skill example, and contrasts ADK with OpenAI’s Agent SDK.
AI agentsAgent DevelopmentGoogle ADK
0 likes · 18 min read

This article walks through a complete prompt‑engineering workflow—starting from a weak baseline, building an evaluation pipeline, and applying four concrete techniques (clarity, specificity, XML structuring, and examples) that lift a Claude score from 3.4 to over 9, with code, metrics, and real‑world examples.
AIClaudePrompt Optimization
0 likes · 19 min read

This article analyzes a PM‑centric AI collaboration framework that consolidates scattered knowledge, reduces repetitive interruptions, and enables a single product manager to efficiently support a twenty‑person team by structuring context, optimizing prompt usage, and standardizing workflows across product, engineering, design, and operations.
AI collaborationPrompt Optimizationknowledge management
0 likes · 9 min read

This article analyzes why over 40% of Agentic AI projects fail due to inadequate observability, outlines three common pain points—trace blindness, uncontrolled token costs, and untraceable failures—and demonstrates a practical ADB MySQL solution that reconstructs logs, classifies failures with AI functions, quantifies token waste, and generates prompt‑optimization suggestions, all with a few SQL statements.
ADB MySQLAI agentsAgent Observability
0 likes · 10 min read


AI WakaMar 11, 2026 · Artificial Intelligence
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 BedrockLLM
0 likes · 24 min read

This article explains how Qoder’s slash commands can eliminate unnecessary project scans and web searches, showing side‑by‑side comparisons, command file structures, customization tips, and best‑practice recommendations to speed up AI‑assisted coding while saving tokens.
AI codingPrompt OptimizationQoder
0 likes · 8 min read

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.
AILLMPrompt Optimization
0 likes · 18 min read

The article outlines the four major obstacles hindering industry‑specific LLM agents—manual workflow maintenance, poor knowledge reuse, training‑inference inefficiency, and complex reasoning evaluation—and explains how Huawei Noah’s MindScale package tackles each with self‑evolving workflows, automated prompt optimization, and a novel KV‑Embedding cache that slashes token consumption by 5.7× while boosting inference speed up to 70%.
Industry AgentKV-EmbeddingMindScale
0 likes · 7 min read

This article presents a rigorous, multi‑dimensional evaluation of the RAG‑MCP framework versus a full‑tool MCP approach on Amazon Bedrock, showing up to 74% token reduction, higher tool‑selection accuracy, lower latency, and better scalability for large tool sets.
Amazon BedrockLLMPrompt Optimization
0 likes · 21 min read

This article explains the common difficulties of writing effective prompts, introduces the open‑source prompt‑optimizer skill that automatically selects and refines professional prompt frameworks, and provides step‑by‑step instructions for preparing materials, packaging the skill for Claude and Chrome, and installing it via GitHub repositories.
AI codingClaudeGitHub
0 likes · 10 min read


Wuming AIDec 25, 2025 · Artificial Intelligence
This guide walks through the entire process of designing, creating, and installing a Claude Skill that automatically optimizes prompts by selecting the best framework, confirming ambiguities with users, and leveraging progressive loading to handle dozens of prompt templates.
AI codingAI skillsAnthropic
0 likes · 8 min read


Wuming AIDec 21, 2025 · Artificial Intelligence
This article demystifies Claude's Agent Skills by defining their structure, comparing them with Rules and MCP, illustrating progressive disclosure with concrete examples, and providing step‑by‑step installation and usage instructions for both official and custom skills.
AIClaudeMCP
0 likes · 11 min read

This comprehensive tutorial walks you through the entire PromptPilot workflow—from initial setup and prompt generation to iterative optimization, visual debugging, batch testing, and intelligent refinement—showcasing how to create high‑quality, production‑ready prompts for AI agents and applications.
AI toolsPrompt OptimizationPrompt engineering
0 likes · 10 min read

Prompt‑Optimizer is an open‑source tool that uses AI models to automatically refine and compare prompts, offering multi‑model support, security features, and cross‑platform access, while providing step‑by‑step Docker deployment instructions for developers and prompt engineers.
AI toolsDockerLLM
0 likes · 7 min read


ArchitectJun 7, 2025 · Artificial Intelligence
The Mass framework, developed by Google and Cambridge University, automates multi‑agent system design by jointly optimizing prompts and topologies through three staged processes, demonstrating significant performance gains over existing methods across various tasks while highlighting the importance of coordinated prompt‑topology optimization.
AI researchMass frameworkPrompt Optimization
0 likes · 6 min read

We introduce an AIGC‑driven content analysis agent for Taobao that automatically builds a fine‑grained feature taxonomy, multimodally labels images, videos and text, mines causal quality features, and deploys auto‑prompt, memory and LoRA‑based training pipelines, achieving over 90% labeling accuracy, 80% labor savings and double‑digit CTR gains while cutting video generation cost to 25% of GPT‑4o.
AIGCContent AnalysisPrompt Optimization
0 likes · 18 min read

This article introduces the Six Thinking Hats framework, explains its benefits, describes AI agent concepts and platforms, and provides a step‑by‑step guide with prompt examples for creating a low‑cost, fully‑featured Six Thinking Hats assistant using generative AI tools.
AI AgentGenerative AIPrompt Optimization
0 likes · 13 min read

This article introduces the “feeding” prompt technique—using Human: and Assistant: tags to directly supply the desired answer—so AI models like Claude can learn tasks quickly, produce correctly formatted outputs, and solve problems with far fewer trial‑and‑error iterations.
AI promptingClaudePrompt Optimization
0 likes · 6 min read


网易UEDCJan 14, 2019 · Frontend Development
This article examines common issues with registration and login prompt designs—misuse of dialog boxes, unclear messaging, and inconsistent styling—then proposes a unified, scenario‑driven style guide that distinguishes front‑end and back‑end prompts, improves consistency, accuracy, and user flow efficiency.
Design GuidelinesPrompt OptimizationUser Experience
0 likes · 8 min read
