# Beyond End-to-End Video Models: An LLM-Based Multi-Agent System for Educational Video Generation

arXiv: https://arxiv.org/abs/2602.11790 · HTML: https://mlsanity.com/paper/2602.11790/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 42 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 16 of 16)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Seedance 1.0: Exploring the Boundaries of Video Generation Models](https://mlsanity.com/paper/2506.09113/) (2025)
- [Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model](https://mlsanity.com/paper/2512.13507/) (2025)
- [EduAgent: Generative Student Agents in Learning](https://mlsanity.com/paper/2404.07963/) (2024)
- [Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2501.15228/) (2025)
- [Code2Video: A Code-centric Paradigm for Educational Video Generation](https://mlsanity.com/paper/2510.01174/) (2025)
- [MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling](https://mlsanity.com/paper/2508.08487/) (2025)
- [Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis](https://mlsanity.com/paper/2509.09595/) (2025)
- [Large Language Models in Computer Science Education: A Systematic Literature Review](https://mlsanity.com/paper/2410.16349/) (2024)
- [ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers](https://mlsanity.com/paper/2601.04342/) (2026)
- [A Unified Multi-Agent Framework for Universal Multimodal Understanding and Generation](https://mlsanity.com/paper/2508.10494/) (2025)

## Built on by (most cited first, 4 of 4)

- [ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://mlsanity.com/paper/2603.27991/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://mlsanity.com/paper/2603.01912/) (2026)
- [Are Video Models Zero-Shot Learners and Reasoners in Education? EduVideoBench, A Knowledge-Skills-Attitude Benchmark for Educational Video Generation](https://mlsanity.com/paper/2605.26918/) (2026)

## Abstract (arXiv)

Although recent end-to-end video generation models demonstrate impressive performance in visually oriented content creation, they remain limited in scenarios that require strict logical rigor and precise knowledge representation, such as instructional and educational media. To address this problem, we propose LASEV, a hierarchical LLM-based multi-agent system for generating high-quality instructional videos from educational problems. LASEV formulates educational video generation as a multi-objective task that simultaneously demands correct step-by-step reasoning, pedagogically coherent narration, semantically faithful visual demonstrations, and precise audio--visual alignment. To address the limitations of prior approaches--including low procedural fidelity, high production cost, and limited controllability--LASEV decomposes the generation workflow into specialized agents that collaborate through a central Orchestrating Agent, shared production state, explicit quality gates, and iterative critique mechanisms. Specifically, the Orchestrating Agent supervises a Solution Agent for rigorous problem solving, an Illustration Agent that produces executable visualization code, and a Narration Agent for learner-oriented instructional scripts. In addition, all outputs from the working agents are subject to semantic critique, rule-based constraints, and tool-based compilation checks. Rather than directly synthesizing pixels, the system constructs a structured executable video script that is deterministically compiled into synchronized visuals and narration using template-driven assembly rules, enabling fully automated production without manual editing. In large-scale deployments, LASEV achieves a throughput exceeding one million videos per day, delivering over a 95% reduction in cost compared to current industry-standard approaches while maintaining a high acceptance rate.