🤖 AutoGen Multi-Agent Group Chat for LLM Paper Scraping

This project implements a multi-agent AI workflow using Microsoft AutoGen. It scrapes recent arXiv papers related to LLM (Large Language Model) applications and generates a markdown table categorized by domain.

Agents in this project include:

• 🧠 Planner: Breaks down tasks
• 👷 Engineer: Writes scraping and formatting code
• 🧪 Scientist: Categorizes papers by domain
• 🤖 Executor: Executes code automatically
• 👤 Admin: You (initiates the chat)

🧠 Future Scope

You can extend this project with additional agents, such as a Critic:

critic = autogen.AssistantAgent(
    name="Critic",
    system_message="Critic. Double check plan, claims, code from other agents and provide feedback. Check whether the plan includes adding verifiable info such as source URL.",
    llm_config=gpt4_config,
)
# Acts as a reviewer that validates other agents' outputs and enhances reliability

---

🚀 Features

• Multi-agent collaboration via AutoGen
• Scrapes arXiv for recent LLM-related papers
• Extracts: Title, Authors, Summary, Link
• Outputs a structured Markdown table categorized by domain
• Supports Windows .bat for easy execution

---

📂 Project Structure

autogen-arxiv/
│
├── main.py # Main script with AutoGen agent logic
├── .env # API key for OpenAI
├── requirements.txt # Python dependencies
├── .gitignore # Files to ignore in Git
├── run_autogen.bat # Windows helper script
├── README.md # Project overview and usage
└── paper/ # Working dir for Executor (autogenerated)

---

⚙️ Setup Instructions

1. Clone or download this repo

git clone https://github.com/SandeshGitHub2077/autogen_multiagent_groupChat.git
cd autogen_multiagent_groupChat

2. Create a Conda environment

conda create -n autogenenv python=3.10 -y
conda activate autogenenv

3. Install dependencies

pip install -r requirements.txt

4. Set your OpenAI API Key

Create a .env file:

OPENAI_API_KEY=your-openai-api-key-here

5. Run the project

jupyter notebook main.ipynb

Or double-click:

run_autogen.bat