Free SKILL.md scraped from GitHub. Clone the repo or copy the file directly into your Claude Code skills directory.
npx versuz@latest install hiyenwong-ai-collection-collection-skills-ai-agents-evolution-surveygit clone https://github.com/hiyenwong/ai_collection.gitcp ai_collection/SKILL.MD ~/.claude/skills/hiyenwong-ai-collection-collection-skills-ai-agents-evolution-survey/SKILL.md---
name: ai-agents-evolution,-architecture,-and-application
description: Skill for AI agent capabilities
---
# AI Agents: Evolution, Architecture, and Applications
## Description
A comprehensive survey examining AI agents from rule-based systems to modern LLM-integrated architectures. Covers perception, planning, and tool use modules, evaluation frameworks balancing effectiveness, efficiency, robustness, and safety. Analyzes applications across enterprise, personal assistance, and specialized domains.
**Key Topics:**
- Evolution from rule-based to LLM-integrated agents
- Architecture: perception, planning, tool use
- Evaluation framework: effectiveness, efficiency, robustness, safety
- Real-world applications and deployments
## Tools Used
- read: Load agent configurations
- write: Save agent designs
- exec: Run agent evaluations
- browser: Access agent frameworks
- memory_search: Retrieve agent patterns
## Instructions for Agents
### Agent Architecture Components
1. **Perception Module** - Process inputs from environment
2. **Planning Module** - Reasoning and decision-making
3. **Tool Use Module** - Interface with external tools
4. **Memory Module** - Maintain state and knowledge
### Evaluation Dimensions
- Effectiveness - Task success rate
- Efficiency - Resource utilization
- Robustness - Error handling
- Safety - Risk mitigation
## Overview
**Source:** arXiv:2503.12687v1
**Utility:** 0.90
**Scope:** 52 pages, comprehensive survey
## Activation Keywords
- AI agent evolution
- agent architecture
- LLM agent survey
- agent evaluation framework
---
## Agent Evolution
| Generation | Characteristics |
|------------|-----------------|
| Rule-based | Static rules, limited adaptability |
| Learning-based | ML models, pattern recognition |
| LLM-integrated | Natural language, reasoning, tools |
---
## Core Architecture
```
Environment Input → Perception → Planning → Tool Use → Action
↑ ↓
Memory ←────────┘
```
---
## Evaluation Framework
| Dimension | Metrics |
|-----------|---------|
| Effectiveness | Success rate, accuracy |
| Efficiency | Time, resource usage |
| Robustness | Error recovery rate |
| Safety | Risk incidents, violations |
---
## Applications
| Domain | Use Cases |
|--------|-----------|
| Enterprise | Customer service, automation |
| Personal | Assistants, scheduling |
| Specialized | Healthcare, finance |
---
## Examples
### Example 1: Basic Application
**User:** I need to apply AI Agents: Evolution, Architecture, and Applications to my analysis.
**Agent:** I'll help you apply ai-agents-evolution-survey. First, let me understand your specific use case...
**Context:** Apply the methodology
### Example 2: Advanced Scenario
**User:** Complex analysis scenario
**Agent:** Based on the methodology, I'll guide you through the advanced application...
### Example 2: Advanced Application
**User:** What are the key considerations for ai-agents-evolution-survey?
**Agent:** Let me search for the latest research and best practices...
## References
- Paper: https://arxiv.org/abs/2503.12687
- DOI: https://doi.org/10.48550/arXiv.2503.12687
---
**Created:** 2026-03-29
**Source:** arXiv:2503.12687v1 - "AI Agents: Evolution, Architecture, and Real-World Applications"