# DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluation

arXiv: https://arxiv.org/abs/2605.30090 · HTML: https://mlsanity.com/paper/2605.30090/

## 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 23 of its 36 references that are in the map.
- First posted on arXiv 28 May 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, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200k](https://mlsanity.com/paper/2503.09642/) (2025)
- [DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation](https://mlsanity.com/paper/2406.16855/) (2024)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [Video-Bench: Human-Aligned Video Generation Benchmark](https://mlsanity.com/paper/2504.04907/) (2025)
- [HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives](https://mlsanity.com/paper/2510.20822/) (2025)
- [MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling](https://mlsanity.com/paper/2508.08487/) (2025)
- [Hollywood Town: Long-Video Generation via Cross-Modal Multi-Agent Orchestration](https://mlsanity.com/paper/2510.22431/) (2025)
- [Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization](https://mlsanity.com/paper/2604.07343/) (2026)
- [LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation](https://mlsanity.com/paper/2603.20192/) (2026)
- [MobileViCLIP: An Efficient Video-Text Model for Mobile Devices](https://mlsanity.com/paper/2508.07312/) (2025)

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

- [Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation](https://mlsanity.com/paper/2607.26694/) (2026)
- [CineForge: Self-Improving Agents for Long-Horizon Video Generation](https://mlsanity.com/paper/2608.29621/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation](https://mlsanity.com/paper/2609.00646/) (2026)

## Abstract (arXiv)

Long-form video generation is rapidly moving from short, single-scene synthesis toward minute-long, multi-shot creation with narrative structure, cinematic control, audio, and cross-modal synchronization. However, evaluating such videos remains challenging, since existing benchmarks largely focus on local visual quality, short-horizon temporal consistency, or generic prompt alignment, and provide limited diagnosis of workflow failures and user-dependent preferences. We introduce DirectorBench, a personalized multi-agent diagnostic benchmark for long-form video generation. DirectorBench evaluates generated videos with respect to 80 structured metadata entries, 7 user profiles, and 40 checkpoint criteria across 5 dimensions: script, visual, audio, cross-modal, and stability. Instead of reducing quality to a single aggregate score, DirectorBench localizes checkpoint-level bottlenecks and supports profile-aware evaluation. We evaluate 4 long-form video generation workflows, 6 base LLMs, and 7 user profiles. Across workflows, DirectorBench reveals a between-unit bottleneck: transition quality averages only 0.256 and reaches 0.356 for the best workflow, while prompt-level user demand fulfillment averages 0.71. We further conduct human evaluation with 14 annotators to validate the alignment between DirectorBench and human judgment. The results show that DirectorBench captures human-perceptible quality differences and reveals workflow- and profile-dependent failure modes that are hidden by aggregate scoring. These findings highlight the importance of diagnostic and profile-aware benchmarking for long-form video generation.