• Lecture

Agents

Agents

Intro

Inner Monologue

以大型語言模型打造的AI Agent

LLM Agent Paper List

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

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

ADAS

Paper: Automated Design of Agentic Systems
Code: https://github.com/ShengranHu/ADAS

Gödel Agent

Paper: Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement
Code: https://github.com/Arvid-pku/Godel_Agent

Voyager

Paper: Voyager: An Open-Ended Embodied Agent with Large Language Models
Code: https://github.com/MineDojo/Voyager

NPCpy

Code: https://github.com/NPC-Worldwide/npcpy

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

LangChain

Kaggle:

HuggingFace smolagents

Examples:

Kaggle:

DSPy

DSPy: Programming—not prompting—Foundation Models

Kaggle:

Blog: Building and Optimizing AI Applications with DSPy and Gemini Flash 2.5

AG2

Kaggle:

AutoGen

MCP (Model Context Protocol)

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

MCP SDK

AgentGym

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

DGM

Paper: Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
Code: https://github.com/jennyzzt/dgm

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。



This site was last updated December 09, 2025.

  • genai