Lecture

Agents

15 Sep 2025

Intro

The Birth of An Agent: Construction of LLM-based Agents

AI Agents Architecture

Paper: AI Agents: Evolution, Architecture, and Real-World Applications

AI Agent 擬人化角色與分工

Automation

from npcpy.npc_compiler import NPC
simon = NPC(
          name='Simon Bolivar',
          primary_directive='Liberate South America from the Spanish Royalists.',
          model='gemma3:4b',
          provider='ollama'
          )
response = simon.get_llm_response("What is the most important territory to retain in the Andes mountains?")
print(response['response'])

Frameworks

OpenAI Agent SDK

Code: https://github.com/openai/openai-agents-python
pip install openai-agents

AG2: Open-Source AgentOS for AI Agents

Kaggle :

AgentGym

Paper: AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
Code: https://github.com/WooooDyy/AgentGym

AgentGym-RL

Paper: AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
Code: https://github.com/WooooDyy/AgentGym-RL

Modular System Design of AgentGym-RL

Post-Training Strategies

AgentGym-RL supports a suite of mainstream online RL algorithms: PPO, GRPO, RLOO, REINFORCE++.
Beyond online RL, AgentGym-RL also supports a broad range of complementary training paradigms: SFT, DPO, AgentEvol.

ScalingInter-RL: Progressive Scaling Interaction for Agent RL

AgentScope

Paper: AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications
Github: https://github.com/agentscope-ai/agentscope

Memento

Paper: Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
Code: https://github.com/Agent-on-the-Fly/Memento
Methodology: Memory-Based MDP with Case-based Reasoning Policy

Alpha Evolve

Blog: AlphaEvolve：Google DeepMind 開創 AI 演算法自主進化新紀元
Paper: AlphaEvolve: A coding agent for scientific and algorithmic discovery

OpenEvolve

Code: https://github.com/algorithmicsuperintelligence/openevolve
Turn your LLMs into autonomous code optimizers that discover breakthrough algorithms

ShinkaEvolve

Paper: ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
Code: https://github.com/SakanaAI/ShinkaEvolve

AlphaResearch

Paper: AlphaResearch: Accelerating New Algorithm Discovery with Language Models
Code: https://github.com/alpharesearchbot/Alpha

GSW (Generative Semantic Workspaces)

Paper: Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces

Fara-7B

Paper: Fara-7B: An Efficient Agentic Model for Computer Use
Code: https://github.com/microsoft/fara

Google ADK

Blog: Building AI Agents Visually with Google ADK Visual Agent Builder

Research the latest developments in quantum computing error correction in 2024.

Google Antigravity

Blog: Google Antigravity
「反重力」系統它內部有好幾個AI代理（Agent），就像一個項目團隊：

「規劃師」代理：負責把你的模糊目標，拆解成具體的、可執行的步驟。
「研究員」代理：負責上網查找最新的天氣API接口是什麼，最好的UI設計長什麼樣。
「構建師」代理：負責根據規劃和研究，吭哧吭哧地寫代碼。
「測試員」代理：負責檢查代碼有沒有bug。
「反思者」代理：負責評估整個過程，看看哪裡可以改進。

MCP - Model Context Protocol

MCP (Model Context Protocol) is an open-source standard for connecting AI applications to external systems.
Blog: Standardizing AI Tooling with Model Context Protocol (MCP)

MCP Servers

Current reference servers

Everything - Reference / test server with prompts, resources, and tools
Fetch - Web content fetching and conversion for efficient LLM usage
Filesystem - Secure file operations with configurable access controls
Git - Tools to read, search, and manipulate Git repositories
Memory - Knowledge graph-based persistent memory system
Sequential Thinking - Dynamic and reflective problem-solving through thought sequences
Time - Time and timezone conversion capabilities

MCP SDK

MCP Inspector

npx -y @modelcontextprotocol/inspector npx <package-name> <args>
# For example
npx -y @modelcontextprotocol/inspector npx @modelcontextprotocol/server-filesystem /Users/username/Desktop

A2A - Agent2Agent Protocol

An open protocol enabling communication and interoperability between opaque agentic applications.

Github” https://github.com/a2aproject/A2A

A2A-SDK

Agent Skills

The Skills architecture

my-skill/
├── SKILL.md          # Required: instructions + metadata
├── scripts/          # Optional: executable code
├── references/       # Optional: documentation
└── assets/           # Optional: templates, resources

Github: https://github.com/anthropics/skills

Agent Coding Tool

Claude Code

Install Claude Code curl -fsSL https://claude.ai/install.sh | bash

OpenCode

# YOLO
curl -fsSL https://opencode.ai/install | bash

# Package managers
npm i -g opencode-ai@latest        # or bun/pnpm/yarn

Skills

Antropics skills

NotebookLM-skill

Install:

mkdir -p ~/.claude/skills
cd ~/.claude/skills
git clone https://github.com/PleasePrompto/notebooklm-skill notebooklm

Run agentic coding tool:

claude or opencode

Inputs:

What are my skills?

Set up NotebookLM authentication

Add this NotebookLM to my library : https://notebooklm.google.com/notebook/c2e2c6de-0131-420e-8686-2326bc9a438a

What is Agent Skills ?

UIUX-Pro-Max-skill

Install:

npm install -g uipro-cli

uipro init --ai claude # Claude Code
uipro init --ai gemini # Gemini
uipro init --ai trae # Trae
uipro init --ai opencode # OpenCode

Go to project:

cd ~/GenAI/Skills/notebooklm

Run agentic coding tool:

claude or opencode

Inputs:

Build a landing page for my SaaS product

OpenClaw

OpenClaw Architecture

Blog: OpenClaw (Clawdbot) Architecture: Engineering Reliable and Controllable AI Agents

The 6-Stage Execution Pipeline:

Channel Adapter: Standardizes inputs from different platforms (e.g., Discord or Telegram) into a unified message format while extracting necessary attachments.
Gateway Server: Acts as a session coordinator, determining which session a message belongs to and assigning it to the appropriate queue.
Lane Queue: A critical reliability layer that enforces serial execution by default, allowing parallelism only for explicitly marked low-risk tasks.
Agent Runner: The “assembly line” for the model. It handles model selection, API key cooling, prompt assembly, and context window management.
Agentic Loop: The iterative cycle where the model proposes a tool call, the system executes it, the result is backfilled, and the loop continues until a resolution is reached or limits are hit.
Response Path: Streams final content back to the user channel while simultaneously writing the entire process to a JSONL transcript for auditing and replay.

OpenClaw Installation

setup VPN : Tailscale

curl -fsSL <https://tailscale.com/install.sh> | sh
sudo tailscale up

setup Firewall

sudo apt install ufw -y
sudo ufw default deny incoming
sudo ufw default allow outgoing
sudo ufw allow in on tailscale0 to any port 22
sudo ufw enable #Type 『y』 to confirm`
sudo ufw status

install OpenClaw

npm install -g openclaw@latest
openclaw onboard --install-daemon
openclaw gateway restart
open browser http://127.0.0.1:18789

.openclaw/openclaw.json

Multiple Agents

This site was last updated February 04, 2026.

agent
mcp
skills

Agents

Intro

The Birth of An Agent: Construction of LLM-based Agents

AI Agents Architecture

AI Agent 擬人化角色與分工

Automation

ADAS

Voyager

NPCpy

Frameworks

Kaggle :

AgentGym

AgentGym-RL

Modular System Design of AgentGym-RL

Post-Training Strategies

ScalingInter-RL: Progressive Scaling Interaction for Agent RL

AgentScope

Memento

OpenEvolve

ShinkaEvolve

GSW (Generative Semantic Workspaces)

Fara-7B

Google ADK

Google Antigravity

Current reference servers

A2A-SDK

The Skills architecture

Agent Coding Tool

Skills

Install:

Run agentic coding tool:

Inputs:

Install:

Go to project:

Run agentic coding tool:

Inputs:

OpenClaw Architecture

OpenClaw Installation

setup VPN : Tailscale

setup Firewall

install OpenClaw

Multiple Agents