Pith. sign in

REVIEW 28 cited by

Automated Movie Generation via Multi-Agent CoT Planning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.07314 v1 pith:QZFVMRGB submitted 2025-03-10 cs.CV

Automated Movie Generation via Multi-Agent CoT Planning

classification cs.CV
keywords movieagentautomatedgenerationcharactermovieplanningcinematographyconsistency
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Existing long-form video generation frameworks lack automated planning, requiring manual input for storylines, scenes, cinematography, and character interactions, resulting in high costs and inefficiencies. To address these challenges, we present MovieAgent, an automated movie generation via multi-agent Chain of Thought (CoT) planning. MovieAgent offers two key advantages: 1) We firstly explore and define the paradigm of automated movie/long-video generation. Given a script and character bank, our MovieAgent can generates multi-scene, multi-shot long-form videos with a coherent narrative, while ensuring character consistency, synchronized subtitles, and stable audio throughout the film. 2) MovieAgent introduces a hierarchical CoT-based reasoning process to automatically structure scenes, camera settings, and cinematography, significantly reducing human effort. By employing multiple LLM agents to simulate the roles of a director, screenwriter, storyboard artist, and location manager, MovieAgent streamlines the production pipeline. Experiments demonstrate that MovieAgent achieves new state-of-the-art results in script faithfulness, character consistency, and narrative coherence. Our hierarchical framework takes a step forward and provides new insights into fully automated movie generation. The code and project website are available at: https://github.com/showlab/MovieAgent and https://weijiawu.github.io/MovieAgent.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 28 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling

    cs.CV 2026-07 conditional novelty 7.0

    FilmWorld generates multi-scene films from novels by materializing an explicit evolving world-state trajectory and rendering shots in parallel, beating five agents on its own FilmEval benchmark.

  2. Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning

    cs.CV 2026-07 accept novelty 7.0

    Latent event planning plus event-factorized attention restructures the AR dependency graph so dense video captions can be decoded in parallel with higher accuracy and 3–4× wall-clock speedup.

  3. MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control

    cs.CV 2026-06 conditional novelty 7.0

    MAVIN is a dual-tower diffusion framework that produces temporally aligned multi-shot audio-visual content from hierarchical captions with optional multi-identity image and audio references.

  4. GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling

    cs.CV 2026-06 unverdicted novelty 7.0

    GroundShot introduces entity-grounded shot scheduling with online visual memory to improve consistency in multi-shot video generation and presents GroundBench for entity-level evaluation.

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

    cs.CL 2026-05 unverdicted novelty 7.0

    DirectorBench is a profile-aware diagnostic benchmark that localizes bottlenecks in long-form video generation workflows using structured checkpoints and multi-agent evaluation.

  6. ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation

    cs.CV 2026-05 unverdicted novelty 7.0

    ReCA is a recursive hierarchical context allocation framework that decomposes multi-shot video extrapolation into bounded subproblems solved by frozen short-video generators to improve consistency over prior approaches.

  7. Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration

    cs.CV 2026-05 unverdicted novelty 7.0

    Soap2Soap uses a multi-agent system with dual-bridge consistency via JSON screenplays and visual anchors plus batch keyframe generation to achieve better long-term consistency in cinematic video remaking than commercial APIs.

  8. Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation

    cs.GR 2026-04 unverdicted novelty 7.0

    Cutscene Agent uses a multi-agent LLM system and a new toolkit for game engine control to automate end-to-end 3D cutscene generation, evaluated on the introduced CutsceneBench.

  9. MCSC-Bench: Multimodal Context-to-Script Creation for Realistic Video Production

    cs.MM 2026-04 unverdicted novelty 7.0

    MCSC-Bench is the first large-scale dataset for the Multimodal Context-to-Script Creation task, requiring models to select relevant shots from redundant materials, plan missing shots, and generate coherent scripts wit...

  10. A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation

    cs.CV 2026-04 unverdicted novelty 7.0

    CineAgents is a multi-agent system that builds hierarchical narrative memory via script reverse-engineering and uses iterative planning to produce instruction-driven cinematic video compilations with better coherence ...

  11. Camera Artist: A Multi-Agent Framework for Cinematic Language Storytelling Video Generation

    cs.AI 2026-04 unverdicted novelty 7.0

    Camera Artist is a multi-agent framework introducing a Cinematography Shot Agent with recursive storyboard generation and cinematic language injection to improve narrative consistency and film quality in AI-generated ...

  12. VABench: A Comprehensive Benchmark for Audio-Video Generation

    cs.CV 2025-12 unverdicted novelty 7.0

    VABench is a new multi-dimensional benchmark for evaluating synchronous audio-video generation across text-to-AV, image-to-AV, and stereo tasks.

  13. SlotMem: Character-Addressable Internal Memory for Narrative Long Video Generation

    cs.CV 2026-07 conditional novelty 6.0

    SlotMem keeps a compact, updateable memory slot for each recurring character and injects it only into that character's tokens, reporting improved long-range identity consistency in narrative video generation.

  14. DramaDirector: Geometry-Guided Short Drama Generation

    cs.CV 2026-06 conditional novelty 6.0

    Geometry-indexed depth–pose retrieval plus schema SFT and GRPO planning improves faithfulness, consistency, and controllability of plot-to-short-drama video generation over multi-agent and text-only baselines.

  15. Crayotter: Traceable Multi-Agent Workflows for Long-Form Video Editing

    cs.CV 2026-05 unverdicted novelty 6.0

    Crayotter introduces a traceable three-phase multi-agent workflow for long-form video editing that scores 3.40/5 in human evaluations, outperforming two baselines on 23 themes.

  16. CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning

    cs.CV 2026-05 unverdicted novelty 6.0

    CogPortrait uses MLLM-based hierarchical planning to convert high-level labels into eye keypoints and a conditioned DiT model to produce portrait animations with improved eye-region accuracy on the new EMH benchmark.

  17. EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    EvalVerse is a pipeline-aware benchmark that distills expert cinematic judgments into VLMs to assess 'goodness' metrics like aesthetics and multi-shot coherence alongside basic prompt adherence.

  18. OProver: A Unified Framework for Agentic Formal Theorem Proving

    cs.CL 2026-05 unverdicted novelty 6.0

    OProver-32B achieves top Pass@32 scores on MiniF2F, ProverBench, and PutnamBench by combining continued pretraining with iterative agentic proving, retrieval, SFT on repairs, and RL on unresolved cases using a 6.86M-p...

  19. When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    MAVEN is a multi-agent prompt refinement framework that improves cultural fidelity in text-to-video generation, demonstrated on a new benchmark of 243 prompts and 972 videos across Chinese, American, and Romanian cultures.

  20. When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    MAVEN introduces a multi-agent system for refining prompts in multicultural text-to-video generation and releases a benchmark of 243 prompts and 972 videos showing improved cultural relevance via parallel agent specia...

  21. StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics

    cs.CV 2026-04 unverdicted novelty 6.0

    StoryBlender generates inter-shot consistent editable 3D storyboards using a three-stage pipeline of semantic-spatial grounding, canonical asset materialization, and spatial-temporal dynamics with agent-based verification.

  22. Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation

    cs.CV 2026-07 conditional novelty 5.0

    A frozen video diffusion backbone augmented with low-rank temporal adapters and a recursive prompt bank outperforms prior long-video generation methods on six benchmarks while tuning only 3.8% of parameters.

  23. DramaDirector: Geometry-Guided Short Drama Generation

    cs.CV 2026-06 unverdicted novelty 5.0

    DramaDirector retrieves depth-pose references from real drama shots to guide first-frame and image-to-video synthesis for plot-driven short dramas, paired with the DramaBoard benchmark.

  24. Bridging Creative Intent and Visual Quality: Creator-Driven Recurrent Video Generation with Agentic Feedback Loops

    cs.CV 2026-06 unverdicted novelty 5.0

    CHIEF is a human-in-the-loop video generation system that combines creator direction with LLM-based audience-perspective critiques to improve narrative coherence in AI-generated videos, tested on student-made films up...

  25. CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation

    cs.CV 2026-06 unverdicted novelty 5.0

    Introduces CineDance-1M dataset for multi-shot long-form text-to-audio-video generation along with CineBench and a model adaptation.

  26. BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation

    cs.CV 2026-05 unverdicted novelty 5.0

    BEAT introduces MuVA encoder and Bar-DP algorithm for rhythm-elastic music-guided trailer generation, claiming SOTA results on the new TrailerArena benchmark.

  27. One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems

    cs.CV 2026-05 unverdicted novelty 5.0

    A hierarchical multi-agent framework converts a single sentence into a short drama using debate-based scripting, 3D-grounded first frames for spatial consistency, and multi-stage reviewer loops.

  28. MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control

    cs.CV 2026-06 unverdicted novelty 4.0

    MAVIN proposes boundary-aware attention, ID-aware propagation, a multi-agent scripting pipeline, and the MAVINSet dataset as the first framework for multi-shot audio-visual generation with narrative control, claiming ...