diff --git a/_posts/2024-09-28-AI-Agents.md b/_posts/2024-09-28-AI-Agents.md
deleted file mode 100644
index e6cea481..00000000
--- a/_posts/2024-09-28-AI-Agents.md
+++ /dev/null
@@ -1,253 +0,0 @@
----
-layout: post
-title: AI Agents
-author: [Richard Kuo]
-category: [Lecture]
-tags: [jekyll, ai]
----
-
-Introduction to AI Agents, Langchain, SWE.
-
----
-## AI Agents
-
-
----
-### [LLM Agent Paper List](https://github.com/WooooDyy/LLM-Agent-Paper-List)
-**Paper:** [The Rise and Potential of Large Language Model Based Agents: A Survey](https://arxiv.org/abs/2309.07864)
-
-
----
-### Survey of LLM-based AI Agents
-**Paper:** [An In-depth Survey of Large Language Model-based Artificial Intelligence Agents](https://arxiv.org/abs/2309.14365)
-
-
-
-**Blog:** [4 Autonomous AI Agents you need to know](https://towardsdatascience.com/4-autonomous-ai-agents-you-need-to-know-d612a643fa92)
-
----
-### Camel
-Communicative Agents for “Mind” Exploration of Large Language Model Society
-**Code:** [https://github.com/camel-ai/camel](https://github.com/camel-ai/camel)
-
-
----
-### AutoGPT
-**Paper:** [Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions](https://arxiv.org/abs/2306.02224)
-**Code:** [https://github.com/Significant-Gravitas/Auto-GPT](https://github.com/Significant-Gravitas/Auto-GPT)
-**Blog:** [AutoGPT architecture & breakdown](https://www.georgesung.com/ai/autogpt-arch/)
-
-
-**Tutorials:** [AutoGPT Forge](https://aiedge.medium.com/autogpt-forge-e3de53cc58ec)
-
-
----
-### [AgentGPT](https://agentgpt.reworkd.ai/)
-**Code:** [https://github.com/reworkd/AgentGPT](https://github.com/reworkd/AgentGPT)
-
----
-### [BabyAGI](https://github.com/yoheinakajima/babyagi)
-**Blog:** [Task-driven Autonomous Agent Utilizing GPT-4, Pinecone, and LangChain for Diverse Applications](https://yoheinakajima.com/task-driven-autonomous-agent-utilizing-gpt-4-pinecone-and-langchain-for-diverse-applications/)
-
-
-**Colab:**
-* [baby_agi.ipynb](https://github.com/langchain-ai/langchain/blob/master/cookbook/baby_agi.ipynb)
-* [baby_agi_with_agent.ipynb](https://github.com/langchain-ai/langchain/blob/master/cookbook/baby_agi_with_agent.ipynb)
-
----
-### [Godmode](https://godmode.space/?ref=futuretools.io)
-
----
-### Voyager
-**Paper:** [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://arxiv.org/abs/2305.16291)
-**Code:** [https://github.com/MineDojo/Voyager](https://github.com/MineDojo/Voyager)
-
-
----
-### Talk2Drive
-**Paper:** [Large Language Models for Autonomous Driving: Real-World Experiments](https://arxiv.org/abs/2312.09397)
-
-
-
----
-### MemGPT
-**Paper:** [MemGPT: Towards LLMs as Operating Systems](https://arxiv.org/abs/2310.08560)
-**Code:** [https://github.com/cpacker/MemGPT](https://github.com/cpacker/MemGPT)
-
-
----
-### [RL-GPT](https://sites.google.com/view/rl-gpt/)
-**Paper:** [RL-GPT: Integrating Reinforcement Learning and Code-as-policy](https://arxiv.org/abs/2402.19299)
-
-
----
-### MC-Planner
-**Paper:** [https://arxiv.org/abs/2302.01560](https://arxiv.org/abs/2302.01560)
-**Code:** [https://github.com/CraftJarvis/MC-Planner](https://github.com/CraftJarvis/MC-Planner)
-
-
----
-## Multi-Agent
-
-### Generative Agents
-**Paper:** [Generative Agents: Interactive Simulacra of Human Behavior](https://arxiv.org/abs/2304.03442)<
-**Code:** [https://github.com/joonspk-research/generative_agents](https://github.com/joonspk-research/generative_agents)
-**[Demo](https://reverie.herokuapp.com/arXiv_Demo/#)**
-
-
-**Blog:** [Paper Review: Generative Agents: Interactive Simulacra of Human Behavior](https://artgor.medium.com/paper-review-generative-agents-interactive-simulacra-of-human-behavior-cc5f8294b4ac)
-
-
-
-
----
-### Multi-Agent Collaboration
-
-* [“Communicative Agents for Software Development,” Qian et al. (2023) (the ChatDev paper)](https://arxiv.org/abs/2307.07924)
-* [“AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation,” Wu et al. (2023)](https://arxiv.org/abs/2308.08155)
-* [“MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework,” Hong et al. (2023)](https://arxiv.org/abs/2308.00352)
-
----
-### Multi-Agent examples
-* [multi-agent-collaboration.ipynb](https://github.com/langchain-ai/langgraph/blob/main/examples/multi_agent/multi-agent-collaboration.ipynb)
-
-
-* [hierarchical_agent_teams.ipynb](https://github.com/langchain-ai/langgraph/blob/main/examples/multi_agent/hierarchical_agent_teams.ipynb)
-
-
-* [agent_supervisor.ipynb](https://github.com/langchain-ai/langgraph/blob/main/examples/multi_agent/agent_supervisor.ipynb)
-
-
----
-### LangGraph + Llama3 + Groq
-**Colab:** [https://drp.li/X3hpZ](https://drp.li/X3hpZ)
-
-
----
-## Frameworks
-
-### [LangChain](https://github.com/langchain-ai/langchain)
-* [LangChain documents](https://js.langchain.com/docs/get_started/introduction)
-* [LangChain use-cases](https://js.langchain.com/docs/use_cases)
-* [LangChain cookbook](https://github.com/langchain-ai/langchain/tree/master/cookbook)
-
----
-### [LangGraph](https://langchain-ai.github.io/langgraph/)
-**[Introduction to LangGraph](https://langchain-ai.github.io/langgraph/tutorials/introduction/)**
-
-
----
-## SWE
-
-### OpenDevin
-**Paper:** [SWE-AGENT: AGENT-COMPUTER INTERFACES ENABLE AUTOMATED SOFTWARE ENGINEERING](https://swe-agent.com/paper.pdf)
-**Code:** [https://github.com/OpenDevin/OpenDevin](https://github.com/OpenDevin/OpenDevin)
-**Docs:** [OpenDevin Intro](https://opendevin.github.io/OpenDevin/modules/usage/intro)
-
-
-
----
-### DroidAgent
-**Paper:** [Autonomous Large Language Model Agents Enabling Intent-Driven Mobile GUI Testing](https://arxiv.org/abs/2311.08649)
-**Code:** [DroidAgent: Intent-Driven Android GUI Testing with LLM Agents](https://github.com/coinse/droidagent)
-
-
----
-### WebVoyager
-**Paper:** [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://arxiv.org/abs/2401.13919)
-**Code:** [https://github.com/MinorJerry/WebVoyager](https://github.com/MinorJerry/WebVoyager)
-
-
----
-### AutoCodeRover
-**Paper:** [AutoCodeRover: Autonomous Program Improvement](https://arxiv.org/html/2404.05427v1)
-
-
-
----
-### [Chain of thought and ReAct — SQL Agent](https://abvijaykumar.medium.com/prompt-engineering-chain-of-thought-and-react-sql-agent-85fa42575c06)
-
-1. **Thought**: The reasoning step, or thought, serves as a guide to the Foundation model, demonstrating how to approach a problem. It involves formulating a sequence of questions that lead the model to the desired solution.
-2. **Action**: Once the thought is established, the next step is to define an action for the Foundation model to take. This action typically involves invoking an API from a predefined set, allowing the model to interact with external resources.
-3. **Observation**: Following the action, the model observes and analyzes the results. The observations become crucial input for further reasoning and decision-making.
-
-#### List chain-of-thought steps:
-
-
-#### List ReAct steps:
-
-
-
-
----
-### ADAS
-**Paper:** [Automated Design of Agentic Systems](https://arxiv.org/abs/2408.08435)
-**Code:** [https://github.com/ShengranHu/ADAS](https://github.com/ShengranHu/ADAS)
-
-
----
-### [Gödel Agent](https://arxiv.org/html/2410.04444v1)
-**Paper:** [Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement](https://arxiv.org/abs/2410.04444)
-
-語言模型隨著代理系統(agentic system)的發展，在推理、工作規畫等領域有很大幅度的進步，這些代理系統(agentic system)主要可以分為兩大類，一是固定整個工作流與工作模組的Hand-Designed Agent；另外一種則是允許較彈性的工作流，並讓Agent可以適度選用工具的Meta-Learning Optimized Agents。但這兩者皆是基於人類先驗經驗而設計的系統，它將受限於人類的經驗，使得整個系統失去最佳化的可能性。
-本篇論文的研究團隊，嘗試利用哥德爾機(Gödel machine)的概念，讓Agent可以自行決定工作流程，自行選用工具模組，並依照環境反饋，自我改良整個工作系統，研究團隊將其稱為Gödel Agent。
-
-在這篇概念性的論文中，研究團隊指出如果要能實現自我優化，Gödel Agent至少需具備四種能力：
-1. **自我覺察(Self-Awareness)**
-能夠讀取工作流當下，環境與Agent的各式變數、函式、類等參數值，取得整體的運作狀態(operating state)。
-
-2. **自我改善(Self-Improvement)**
-能夠利用推理與規劃的能力，針對當下狀況，認知到應該調整那些工作區塊，並進而調整程式碼去修改工作邏輯。
-
-3. **與環境互動(Environmental Interaction)**
-針對當前修改的結果，可以由環境的狀態變化取得反饋，得知目前的策略是否成功，並評估是否需要再度調整。
-
-4. **持續改進(Recursive Improvement)**
-利用前三項能力，不停迭代，在經過幾次迭代後，這將產生類似Gödel machine的效果，以達到整個系統的最佳化。
-
-研究團隊給予Gödel Agent幾種不同的工作類型，測試它的表現，並與過往幾種方法，諸如CoT、Self-Refine、Role Assignment、Meta Agent Search進行比較，就結果上來說Gödel Agent完勝，不過由於測試的工作類型較侷限，目前尚未知道Gödel Agent在不同的領域是否都如此出色。
-研究團隊也給出未來的研究方向，例如語言模型能否產生集體智慧(collective Intelligence)，或者Gödel Agent是否確實達到系統理論上的最佳化(theoretical optimality)等，都是有趣的研究主題。
-
----
-### [OpenAI Swarm](https://github.com/openai/swarm)
-
-
-#### llama3-groq
-```
-import openai
-from google.colab import userdata
-
-model = "llama3-groq-70b-8192-tool-use-preview"
-
-llm_client = openai.OpenAI(
- base_url="https://api.groq.com/openai/v1",
- api_key=userdata.get('GROQ_API_KEY'),
-)
-```
-
-#### bare_minimum
-```
-# https://github.com/openai/swarm/blob/main/examples/basic/bare_minimum.py
-from swarm import Swarm, Agent
-
-swarm_client = Swarm(client=llm_client)
-
-agent = Agent(
- name="Agent",
- instructions="You are a helpful agent.",
- model=model,
- tool_choice="auto"
-)
-
-messages = [{"role": "user", "content": "Hi!"}]
-response = swarm_client.run(agent=agent, messages=messages)
-
-print(response.messages[-1]["content"])
-```
-
-#### [Swarm_Llama3-Groq.ipynb](https://colab.research.google.com/github/sbagency/AI-agents-hacks/blob/main/Openai_swarm_Llama3_Groq_ipynb%22.ipynb)
-
-
-
-
-*This site was last updated {{ site.time | date: "%B %d, %Y" }}.*