Movie2Game-Bench: Holistic Evaluation of Film-to-Game Adaptation Beyond Playability
Summary
该论文提出 Movie2Game-Bench(M2G-bench),一个超越可玩性的电影改编游戏综合评估基准,包含22部电影和658个参考项,对14个模型在游戏质量、改编保真度与玩家体验方面进行评测,并揭示了可玩序列生成的普遍短板。
View Cached Full Text
Cached at: 11/19/26, 07:27 AM
Paper page - Movie2Game-Bench: Holistic Evaluation of Film-to-Game Adaptation Beyond Playability
Source: https://huggingface.co/papers/2611.24669
Abstract
Adaptingafilmintoagamerequiresselectingsourceelementsandtranslatingthemintoplayeractions,rules,andfeedback.WeintroduceMovie2Game-Bench(M2G-bench),abenchmarkforevaluatingfilm-to-gameadaptationbeyondplayability.M2G-benchcombinesgeneralevaluation,movie-specificevaluation,andplaytestingbythreeGUImodelplayers.Theprotocolconnectssourcecontenttogameplaystepsandimplementationevidence,capturingbothcontentpreservationandinteractiverealization.Thebenchmarkcomprises22filmsand658source-specificreferenceitems.Evaluating14modelsonthesamefilmswiththeirselectedprimaryharnessesrevealscomplementarystrengthsingamequality,adaptation,andplayerexperience.Asharedweaknessconcernsplayablesequences:thiscategoryhasthelowestcontent-presencemeaninall14models,averaging37.9outof100comparedwith54.8foriconicelements.Amongjudgmentsofretainedemotionaldevelopmentcontent,narrativechoicesaccountfor60.0%andscenariooperationfor7.2%.Thesefindingsidentifytwolinkedprioritiesforfilm-to-gameadaptation:preservingsourcesituationsthatcansupportgameplayandconnectingretainedcontenttoplayeractionsandconsequences.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2611\.24669
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2611.24669 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2611.24669 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2611.24669 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
FilmBench: A Film-Grade Benchmark for Cinematic Video Generation
FilmBench is a new benchmark for cinematic video generation, using prompts derived from award-winning films across 20 genres and a three-level cinematic taxonomy with 35+ sub-metrics. It includes an open-source automatic evaluation agent (FilmOps) that reproduces human model rankings with high correlation, revealing significant gaps in dynamic aesthetics and multi-shot performance compared to prior web-style benchmarks.
GameCommBench: A Unified Benchmark and Type-Aware Evaluation for AI-Generated Game Commentary
提出了 GameCommBench,一个覆盖棋类、体育和电竞的统一 AI 游戏解说基准,并提出类型感知解说评估框架 TACE,揭示实况观察和策略分析是 AI 解说的主要瓶颈。
A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?
论文提出 A2Z GameSpec-Bench,一个包含 100 份长篇游戏设计文档(GDD)的基准,用于评估编码代理在端到端游戏开发中遵循互锁需求的能力。结果显示现有代理在同时满足代码实现与实际游玩的联动需求上表现不佳,而需求级反馈可在两轮修订后将 GDD 忠实度提升 10.9%。
OCTAVE: A Capability-Resolved Benchmark for End-to-End HTML5 Game Generation
OCTAVE 是一个针对端到端 HTML5 游戏生成的能力分解基准,包含 8 个能力维度、180 个任务和 1,800 条评估要求;对 11 个模型-工具链组合的评测显示最佳组合的通过率仍不足 50%,揭示了 AI 代理在完整游戏开发中的显著差距。
GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?
The paper introduces GameXpert-Bench, a benchmark with three tracks to evaluate coding agents' game development capabilities across creation, bug repair, and optimization. It finds that current agents are better at initial generation than at defect discovery and multi-turn optimization.