TheoremExplainAgent (TEA) 🍵

🌐 Homepage | 📖 arXiv | 🤗 HuggingFace Dataset | 🎥Video Data | ▶️ YouTube

This repo contains the codebase for our paper TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding

ACL 2025 main (Oral)

Introduction

TheoremExplainAgent is an AI system that generates long-form Manim videos to visually explain theorems, proving its deep understanding while uncovering reasoning flaws that text alone often hides.

https://github.com/user-attachments/assets/17f2f4f2-8f2c-4abc-b377-ac92ebda69f3

📰 News

2025 Jun 24: Paper got selected for Oral presentation (Top 3%).
2025 Jun 8: We released our generated video data for researchers to serve as baselines.
2025 May 15: Paper accepted to ACL 2025 main conference.
2025 Mar 3: Generation code and Evaluation code released. Thanks for the wait!

2025 Feb 27: Paper available on Arxiv. Thanks AK for putting our paper on HF Daily.

Downloading Generated Video Data

Skip this section if you just want to try out the code. If you are researchers who just need the baseline videos as baseline comparison, download it here:

wget --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate 'https://docs.google.com/uc?export=download&id=18kmzXvbxaFGyJw-g51jnq9m93v_ez4aJ' -O /tmp/gdrive.html && wget --load-cookies /tmp/cookies.txt -O baseline_videos.zip "https://drive.usercontent.google.com/download?id=18kmzXvbxaFGyJw-g51jnq9m93v_ez4aJ&export=download&confirm=$(sed -rn 's/.*name="confirm" value="([^"]+)".*/\\1/p' /tmp/gdrive.html)&uuid=$(sed -rn 's/.*name="uuid" value="([^"]+)".*/\\1/p' /tmp/gdrive.html)" && rm /tmp/gdrive.html /tmp/cookies.txt

Installation

Look at the FAQ section in this README doc if you encountered any errors. If that didnt help, create a issue<br>

Setting up conda environment

conda create --name tea python=3.12.8
conda activate tea
pip install -r requirements.txt

You may also need to install latex and other dependencies for Manim Community. Look at Manim Installation Docs for more details.

# You might need these dependencies if you are using Linux Ubuntu:
sudo apt-get install portaudio19-dev
sudo apt-get install libsdl-pango-dev

Then Download the Kokoro model and voices using the commands to enable TTS service.

mkdir -p models && wget -P models https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files/kokoro-v0_19.onnx && wget -P models https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files/voices.bin

Create .env based on .env.template, filling in the environmental variables according to the models you choose to use. See LiteLLM for reference.

touch .env

Then open the .env file and edit it with whatever text editor you like.

Your .env file should look like the following:

# OpenAI
OPENAI_API_KEY=""

# Azure OpenAI
AZURE_API_KEY=""
AZURE_API_BASE=""
AZURE_API_VERSION=""

# Google Vertex AI
VERTEXAI_PROJECT=""
VERTEXAI_LOCATION=""
GOOGLE_APPLICATION_CREDENTIALS=""

# Google Gemini
GEMINI_API_KEY=""

...

# Kokoro TTS Settings
KOKORO_MODEL_PATH="models/kokoro-v0_19.onnx"
KOKORO_VOICES_PATH="models/voices.bin"
KOKORO_DEFAULT_VOICE="af"
KOKORO_DEFAULT_SPEED="1.0"
KOKORO_DEFAULT_LANG="en-us"

Fill in the API keys according to the model you wanted to use.

Configure Python path. Note that you need to configure the python path to make it work. Otherwise you may encounter import issues (like not being able to import src etc.)

export PYTHONPATH=$(pwd):$PYTHONPATH

(Optional) To setup RAG, See https://github.com/TIGER-AI-Lab/TheoremExplainAgent?tab=readme-ov-file#generation-with-rag.

Look at the FAQ section in this README doc if you encountered any errors. If that didnt help, create a issue<br>

Generation

Supported Models

The model naming follows the LiteLLM convention. For details on how models should be named, please refer to the LiteLLM documentation.

Generation (Single topic)

python generate_video.py \
      --model "openai/o3-mini" \
      --helper_model "openai/o3-mini" \
      --output_dir "output/your_exp_name" \
      --topic "your_topic" \
      --context "description of your topic, e.g. 'This is a topic about the properties of a triangle'" \

Example:

python generate_video.py \
      --model "openai/o3-mini" \
      --helper_model "openai/o3-mini" \
      --output_dir "output/my_exp_name" \
      --topic "Big O notation" \
      --context "most common type of asymptotic notation in computer science used to measure worst case complexity" \

Generation (in batch)

python generate_video.py \
      --model "openai/o3-mini" \
      --helper_model "openai/o3-mini" \
      --output_dir "output/my_exp_name" \
      --theorems_path data/thb_easy/math.json \
      --max_scene_concurrency 7 \
      --max_topic_concurrency 20 \

Generation with RAG

Before using RAG, download the RAG documentation from this Google Drive link. After downloading, unzip the file. For example, if you unzip it to data/rag/manim_docs, then you should set --manim_docs_path to data/rag/manim_docs. The vector database will be created the first time you run with RAG.

python generate_video.py \
            --model "openai/o3-mini" \
            --helper_model "openai/o3-mini" \
            --output_dir "output/with_rag/o3-mini/vtutorbench_easy/math" \
            --topic "Big O notation" \
            --context "most common type of asymptotic notation in computer science used to measure worst case complexity" \
            --use_rag \
            --chroma_db_path "data/rag/chroma_db" \
            --manim_docs_path "data/rag/manim_docs" \
            --embedding_model "vertex_ai/text-embedding-005"

We support more options for generation, see below for more details:

usage: generate_video.py [-h]
                         [--model]
                         [--topic TOPIC] [--context CONTEXT]
                         [--helper_model]
                         [--only_gen_vid] [--only_combine] [--peek_existing_videos] [--output_dir OUTPUT_DIR] [--theorems_path THEOREMS_PATH]
                         [--sample_size SAMPLE_SIZE] [--verbose] [--max_retries MAX_RETRIES] [--use_rag] [--use_visual_fix_code]
                         [--chroma_db_path CHROMA_DB_PATH] [--manim_docs_path MANIM_DOCS_PATH]
                         [--embedding_model {azure/text-embedding-3-large,vertex_ai/text-embedding-005}] [--use_context_learning]
                         [--context_learning_path CONTEXT_LEARNING_PATH] [--use_langfuse] [--max_scene_concurrency MAX_SCENE_CONCURRENCY]
                         [--max_topic_concurrency MAX_TOPIC_CONCURRENCY] [--debug_combine_topic DEBUG_COMBINE_TOPIC] [--only_plan] [--check_status]
                         [--only_render] [--scenes SCENES [SCENES ...]]

Generate Manim videos using AI

options:
  -h, --help            show this help message and exit
  --model               Select the AI model to use
  --topic TOPIC         Topic to generate videos for
  --context CONTEXT     Context of the topic
  --helper_model        Select the helper model to use
  --only_gen_vid        Only generate videos to existing plans
  --only_combine        Only combine videos
  --peek_existing_videos, --peek
                        Peek at existing videos
  --output_dir OUTPUT_DIR
                        Output directory
  --theorems_path THEOREMS_PATH
                        Path to theorems json file
  --sample_size SAMPLE_SIZE, --sample SAMPLE_SIZE
                        Number of theorems to sample
  --verbose             Print verbose output
  --max_retries MAX_RETRIES
                        Maximum number of retries for code generation
  --use_rag, --rag      Use Retrieval Augmented Generation
  --use_visual_fix_code, --visual_fix_code
                        Use VLM to fix code with rendered visuals
  --chroma_db_path CHROMA_DB_PATH

TheoremExplainAgent

Install / Use

README