Research-Assistant-Agent

# 🎓 Multi-Agent Research Assistant

An advanced AI agent system designed to automate the academic research process. Powered by **Google Gemini 2.5**, this project uses a **multi-agent architecture** to search for papers, analyze publication trends, format citations, and persist findings.

## 🚀 Features

* **Multi-Agent Architecture**: Specialized agents working in concert:
    🕵️ **Researcher**: Searches ArXiv for relevant papers (supports parallel queries).
    📊 **Analyst**: Analyzes data (e.g., publication year distribution) and generates ASCII charts.
    📝 **Formatter**: Formats raw paper data into proper APA citations.
    🧠 **Root Agent**: Orchestrates the workflow and manages memory.

* **Tools & Integrations**:
    **ArXiv API**: Real-time access to millions of academic papers.
    **Long-Term Memory**: Persists findings to a JSON knowledge base.
    **Parallel Execution**: Simulates concurrent research tasks for efficiency.

* **Deployment Ready**:
    Run locally via **Flask API**.
    Deploy to production on **Google Cloud Vertex AI Agent Engine**.
    Interactive testing via **ADK Web UI**.

## 🏗️ Architecture

The system follows a hierarchical multi-agent pattern:

```mermaid
graph TD
    User[User Query] --> Root["Root Agent (Orchestrator)"]
    Root -->|Delegates Search| Researcher[Researcher Agent]
    Researcher -->|Calls| ArXiv[ArXiv API]
    Root -->|Delegates Analysis| Analyst[Analyst Agent]
    Root -->|Delegates Formatting| Formatter[Formatter Agent]
    Root -->|Saves Data| Memory[(Long-Term Memory)]
    Root -->|Final Report| User
```

## 🛠️ Tech Stack

* **LLM**: Google Gemini 2.5 Flash Lite
* **Framework**: Google Agent Development Kit (ADK)
* **Language**: Python 3.10+
* **APIs**: ArXiv API
* **Deployment**: Flask, Vertex AI, Docker

## 📦 Installation

1. **Clone the repository**:

    ```bash
    git clone https://github.com/emansarahafi/research-assistant-agent.git
    cd research-assistant-agent
    ```

2. **Install dependenc