Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914513596448768 |
|---|---|
| author | He, Lanshan Pang, Haozhou Gan, Qi Shen, Xin Zhang, Ziwei Liu, Yibo Fang, Gang Liu, Bo Sheng, Kai Zeng, Shengfeng Li, Chaofan Hui, Zhen Zhou, Keer Zhou, Lan Dai, Shujun |
| author_facet | He, Lanshan Pang, Haozhou Gan, Qi Shen, Xin Zhang, Ziwei Liu, Yibo Fang, Gang Liu, Bo Sheng, Kai Zeng, Shengfeng Li, Chaofan Hui, Zhen Zhou, Keer Zhou, Lan Dai, Shujun |
| contents | Cutscenes are carefully choreographed cinematic sequences embedded in video games and interactive media, serving as the primary vehicle for narrative delivery, character development, and emotional engagement. Producing cutscenes is inherently complex: it demands seamless coordination across screenwriting, cinematography, character animation, voice acting, and technical direction, often requiring days to weeks of collaborative effort from multidisciplinary teams to produce minutes of polished content. In this work, we present Cutscene Agent, an LLM agent framework for automated end-to-end cutscene generation. The framework makes three contributions: (1)~a Cutscene Toolkit built on the Model Context Protocol (MCP) that establishes \emph{bidirectional} integration between LLM agents and the game engine -- agents not only invoke engine operations but continuously observe real-time scene state, enabling closed-loop generation of editable engine-native cinematic assets; (2)~a multi-agent system where a director agent orchestrates specialist subagents for animation, cinematography, and sound design, augmented by a visual reasoning feedback loop for perception-driven refinement; and (3)~CutsceneBench, a hierarchical evaluation benchmark for cutscene generation. Unlike typical tool-use benchmarks that evaluate short, isolated function calls, cutscene generation requires long-horizon, multi-step orchestration of dozens of interdependent tool invocations with strict ordering constraints -- a capability dimension that existing benchmarks do not cover. We evaluate a range of LLMs on CutsceneBench and analyze their performance across this challenging task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25318 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation He, Lanshan Pang, Haozhou Gan, Qi Shen, Xin Zhang, Ziwei Liu, Yibo Fang, Gang Liu, Bo Sheng, Kai Zeng, Shengfeng Li, Chaofan Hui, Zhen Zhou, Keer Zhou, Lan Dai, Shujun Graphics Artificial Intelligence Computation and Language Cutscenes are carefully choreographed cinematic sequences embedded in video games and interactive media, serving as the primary vehicle for narrative delivery, character development, and emotional engagement. Producing cutscenes is inherently complex: it demands seamless coordination across screenwriting, cinematography, character animation, voice acting, and technical direction, often requiring days to weeks of collaborative effort from multidisciplinary teams to produce minutes of polished content. In this work, we present Cutscene Agent, an LLM agent framework for automated end-to-end cutscene generation. The framework makes three contributions: (1)~a Cutscene Toolkit built on the Model Context Protocol (MCP) that establishes \emph{bidirectional} integration between LLM agents and the game engine -- agents not only invoke engine operations but continuously observe real-time scene state, enabling closed-loop generation of editable engine-native cinematic assets; (2)~a multi-agent system where a director agent orchestrates specialist subagents for animation, cinematography, and sound design, augmented by a visual reasoning feedback loop for perception-driven refinement; and (3)~CutsceneBench, a hierarchical evaluation benchmark for cutscene generation. Unlike typical tool-use benchmarks that evaluate short, isolated function calls, cutscene generation requires long-horizon, multi-step orchestration of dozens of interdependent tool invocations with strict ordering constraints -- a capability dimension that existing benchmarks do not cover. We evaluate a range of LLMs on CutsceneBench and analyze their performance across this challenging task. |
| title | Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation |
| topic | Graphics Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2604.25318 |