TheoremExplainAgent  by TIGER-AI-Lab

AI system for multimodal theorem explanation via video generation

created 5 months ago
1,348 stars

Top 30.4% on sourcepulse

GitHubView on GitHub
Project Summary

This project provides TheoremExplainAgent (TEA), an AI system designed to generate long-form Manim videos that visually explain mathematical theorems. It targets researchers and educators seeking to deepen LLM understanding of theorems and identify reasoning flaws, offering a multimodal approach to complex concepts.

How It Works

TEA leverages large language models (LLMs) to generate detailed plans for Manim animations, which are then rendered into videos. It supports various LLM providers via LiteLLM and includes an optional Retrieval Augmented Generation (RAG) component for incorporating custom documentation. The system also features an evaluation module that uses LLMs to assess the quality of generated videos.

Quick Start & Requirements

  • Installation: Create a conda environment (conda create --name tea python=3.12.8), activate it (conda activate tea), and install dependencies (pip install -r requirements.txt).
  • Prerequisites: Python 3.12.8, Manim Community (requires LaTeX and potential system dependencies like portaudio19-dev, libsdl-pango-dev on Ubuntu), and LLM API keys (configured via .env file).
  • Model Download: Download Kokoro TTS models.
  • Path Configuration: Set PYTHONPATH=$(pwd):$PYTHONPATH.
  • Documentation: Homepage, arXiv, HuggingFace Dataset.

Highlighted Details

  • Generates Manim videos for theorem explanations.
  • Supports RAG for custom documentation integration.
  • Includes an LLM-based evaluation framework for generated videos.
  • Offers batch processing for multiple theorems.
  • Utilizes Kokoro for Text-to-Speech (TTS) capabilities.

Maintenance & Community

The project is associated with TIGER-AI-Lab and has released code and evaluation components. Further community interaction details are not explicitly provided in the README.

Licensing & Compatibility

  • License: MIT License.
  • Compatibility: The authors state the work is intended for research purposes only and do not endorse commercial applications. Tested on macOS and Linux.

Limitations & Caveats

Evaluation requires specific LLMs (Gemini, GPT-4o) and video/subtitle files. The disclaimer advises against commercial use, and the project is presented "as is" without warranties.

Health Check
Last commit

1 week ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
0
Star History
129 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.