Search papers, labs, and topics across Lattice.
This paper introduces LLM2Manim, a semi-automated, human-in-the-loop pipeline leveraging LLMs to generate STEM animations using the Manim library, incorporating multimedia learning principles. The pipeline employs constrained prompt templates, symbol ledgers, and iterative regeneration to ensure output stability and correctness, with expert review before rendering. A within-subject study with 100 students demonstrated that animation-based instruction resulted in significantly better post-test scores (83% vs. 78%), higher learning gains (d=0.67), increased engagement (d=0.94), and reduced cognitive load (d=0.41) compared to PowerPoint slides.
LLMs can now generate STEM animations that not only improve student learning outcomes but also boost engagement and reduce cognitive load compared to traditional methods.
High-quality STEM animations can be useful for learning, but they are still not common in daily teaching, mostly because they take time and special skills to make. In this paper, we present a semi-automated, human-in-the-loop (HITL) pipeline that uses a large language model (LLM) to help convert math and physics concepts into narrated animations with the Python library Manim. The pipeline also tries to follow multimedia learning ideas like segmentation, signaling, and dual coding, so the narration and the visuals are more aligned. To keep the outputs stable, we use constrained prompt templates, a symbol ledger to keep symbols consistent, and we regenerate only the parts that have errors. We also include expert review before the final rendering, because sometimes the generated code or explanation is not fully correct. We tested the approach with 100 undergraduate students in a within-subject A-B study. Each student learned two similar STEM topics, one with the LLM-generated animations and one with PowerPoint slides. In general, the animation-based instruction gives slightly better post-test scores (83% vs.78%, p<.001), and students show higher learning gains (d=0.67). They also report higher engagement (d=0.94) and lower cognitive load (d=0.41). Students finished the tasks faster, and many of them said they prefer the animated format. Overall, these results suggest LLM-assisted animation can make STEM content creation easier, and it may be a practical option for more classrooms.