Code2Games: Enabling Coding Agents for Gaming World Generation

Hugging Face Daily Papers Papers
agentic-framework game-generation coding-agents benchmark unreal-engine-5 blender world-generation

Summary

Code2Games is an agentic framework that coordinates coding agents to build consistent gaming worlds from natural-language game intents, adapting them to Unreal Engine 5 via execution-guided reconstruction, and introduces the GameCode4D benchmark for evaluating game-world generation quality.

Generating a high-quality gaming world from a natural-language game intent requires joint reasoning about scene structure, spatial layout, gameplay objectives, interactive entities, and executable gameplay logic. Existing coding agents can generate individual assets, scenes, or scripts, but often struggle to maintain consistency across these components. We propose Code2Games, an agentic framework that builds a structured gaming world upon a base Blender world generated from the same game intent. Code2Games coordinates scene analysis, gameplay planning, constrained gaming-world generation, and gaming-engine customization through a shared scene-gameplay representation with persistent element correspondence. After world generation, Code2Games adapts the generated world to Unreal Engine 5 and employs an execution-guided reconstruction process that uses compilation diagnostics, runtime feedback, and gameplay test results to resolve inconsistencies arising during engine adaptation. To systematically evaluate gaming-world generation, we introduce the GameCode4D benchmark, which comprises ten fixed game prompts spanning different levels of scene and gameplay complexity. We evaluate the generated results across four dimensions: visual quality, interactive fidelity, multimodal artifact quality, and playable-game quality. Experiments demonstrate that, compared with direct gaming-world generation by coding agents and existing baseline methods, Code2Games consistently improves the visual quality and interactive fidelity of generated gaming worlds, as well as the quality of the resulting games after engine adaptation.
Original Article
View Cached Full Text

Cached at: 10/06/26, 08:54 AM

Paper page - Code2Games: Enabling Coding Agents for Gaming World Generation

Source: https://huggingface.co/papers/2610.05033

Abstract

Generatingahigh-qualitygamingworldfromanatural-languagegameintentrequiresjointreasoningaboutscenestructure,spatiallayout,gameplayobjectives,interactiveentities,andexecutablegameplaylogic.Existingcodingagentscangenerateindividualassets,scenes,orscripts,butoftenstruggletomaintainconsistencyacrossthesecomponents.WeproposeCode2Games,anagenticframeworkthatbuildsastructuredgamingworlduponabaseBlenderworldgeneratedfromthesamegameintent.Code2Gamescoordinatessceneanalysis,gameplayplanning,constrainedgaming-worldgeneration,andgaming-enginecustomizationthroughasharedscene-gameplayrepresentationwithpersistentelementcorrespondence.Afterworldgeneration,Code2GamesadaptsthegeneratedworldtoUnrealEngine5andemploysanexecution-guidedreconstructionprocessthatusescompilationdiagnostics,runtimefeedback,andgameplaytestresultstoresolveinconsistenciesarisingduringengineadaptation.Tosystematicallyevaluategaming-worldgeneration,weintroducetheGameCode4Dbenchmark,whichcomprisestenfixedgamepromptsspanningdifferentlevelsofsceneandgameplaycomplexity.Weevaluatethegeneratedresultsacrossfourdimensions:visualquality,interactivefidelity,multimodalartifactquality,andplayable-gamequality.Experimentsdemonstratethat,comparedwithdirectgaming-worldgenerationbycodingagentsandexistingbaselinemethods,Code2Gamesconsistentlyimprovesthevisualqualityandinteractivefidelityofgeneratedgamingworlds,aswellasthequalityoftheresultinggamesafterengineadaptation.

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2610\.05033

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/2610.05033 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.05033 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.05033 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

Coding Agent Is Good As World Simulator

arXiv cs.AI

This paper presents an agentic framework that uses coding agents to generate physically plausible world simulations from natural language prompts, outperforming video-based models in physical accuracy and instruction fidelity.

OpenGame: Open Agentic Coding for Games

Papers with Code Trending

OpenGame is an open-source agentic framework for end-to-end web game creation, powered by the specialized GameCoder-27B model and evaluated via the new OpenGame-Bench benchmark.

AgentGarten: Code Worlds for Evolving Agents

Hugging Face Daily Papers

AgentGarten is a framework that couples simulators and game engines with a shared neural renderer to build real-time interactive environments where agents learn from visual observations and distill experience into inherited playbooks, achieving major learning efficiency gains over conventional RL with just 4 rounds of experience.