TIGER-AI-Lab/TheoremExplainAgent: Official Repo for "TheoremExplainAgent: Towards Multimodal Explanations for LLM Theorem Understanding"

Official Repo for "TheoremExplainAgent: Towards Multimodal Explanations for LLM Theorem Understanding"

🌐 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. trailer_caption.mp4 📰 News 2025 Jun 24: Paper got selected for Oral presentation (Top 3%). 2025 Jun 8: We released our generated video data…

saved by

• Chloe Nguyen

related reading

• Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
• TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answeringarxiv.org
• Llama 2 · Hugging Facehuggingface.co
• Video models are zero-shot learners and reasonersarxiv.org
• [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
• Agent Harness for Learning Thingsyoutube.com
• GitHub - THU-MAIC/OpenMAIC: Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one clickgithub.com
• [2603.07267] How to Steal Reasoning Without Reasoning Tracesarxiv.org
• GitHub - EleutherAI/lm-evaluation-harness: A framework for few-shot evaluation of language models. · GitHubgithub.com
• 2501.05874arxiv.org
• [2605.02421] AOCI: Symbolic-Semantic Indexing for Practical Repository-Scale Code Understanding with LLMsarxiv.org
• Dreaming Vectors: Gradient-descented steering vectors from Activation Oracles and using them to Red-Team AOs — LessWronglesswrong.com