AI for Games in the Foundation Model Era

Hugging Face Daily Papers Papers
ai-gaming foundation-models game-ai research-survey game-world-models

Summary

This paper surveys the use of foundation models in game AI across roles like playing, modeling, design, and evaluation, highlighting transferability challenges and the need for game-specific validation.

Foundation models, alongside advances in learned game-world models, are reshaping AI across the game lifecycle. Beyond playing games, recent systems model players and game dynamics, support design and development, adapt player-facing experiences at runtime, and evaluate resulting artifacts. Yet these directions have evolved largely separately, obscuring which capabilities transfer across settings and which remain tied to particular games, engines, interfaces, or player populations. We organize the literature into six roles according to the immediate use of AI output: playing and acting; modeling players and games; designing games; building and maintaining games; generating and adapting at runtime; and testing and evaluating games. For each role, we examine what structure is supplied by the game or workflow, what AI learns or produces, which capabilities and artifacts transfer across settings and roles, and what evidence supports the claims. We identify cross-role connections: trajectories train world models, learned environments provide experience for agents, design specifications drive executable implementations, and play or testing feedback guides revision. However, control schemes, rules, engine interfaces, state representations, and player contexts often remain setting-specific, so downstream claims require validation in the target setting. Evaluation is most standardized for bounded game playing and selected learned environments, while persistent state in learned worlds, repeated software revision, validated player modeling, sustained runtime adaptation, and representative automated testing remain less established. The central challenge is to reuse or transfer outputs and capabilities across roles while re-establishing evidence for effectiveness in the game-specific contexts where they are used.
Original Article
View Cached Full Text

Cached at: 09/16/26, 02:44 AM

Paper page - AI for Games in the Foundation Model Era

Source: https://huggingface.co/papers/2609.16679

Abstract

Foundationmodels,alongsideadvancesinlearnedgame-worldmodels,arereshapingAIacrossthegamelifecycle.Beyondplayinggames,recentsystemsmodelplayersandgamedynamics,supportdesignanddevelopment,adaptplayer-facingexperiencesatruntime,andevaluateresultingartifacts.Yetthesedirectionshaveevolvedlargelyseparately,obscuringwhichcapabilitiestransferacrosssettingsandwhichremaintiedtoparticulargames,engines,interfaces,orplayerpopulations.WeorganizetheliteratureintosixrolesaccordingtotheimmediateuseofAIoutput:playingandacting;modelingplayersandgames;designinggames;buildingandmaintaininggames;generatingandadaptingatruntime;andtestingandevaluatinggames.Foreachrole,weexaminewhatstructureissuppliedbythegameorworkflow,whatAIlearnsorproduces,whichcapabilitiesandartifactstransferacrosssettingsandroles,andwhatevidencesupportstheclaims.Weidentifycross-roleconnections:trajectoriestrainworldmodels,learnedenvironmentsprovideexperienceforagents,designspecificationsdriveexecutableimplementations,andplayortestingfeedbackguidesrevision.However,controlschemes,rules,engineinterfaces,staterepresentations,andplayercontextsoftenremainsetting-specific,sodownstreamclaimsrequirevalidationinthetargetsetting.Evaluationismoststandardizedforboundedgameplayingandselectedlearnedenvironments,whilepersistentstateinlearnedworlds,repeatedsoftwarerevision,validatedplayermodeling,sustainedruntimeadaptation,andrepresentativeautomatedtestingremainlessestablished.Thecentralchallengeistoreuseortransferoutputsandcapabilitiesacrossroleswhilere-establishingevidenceforeffectivenessinthegame-specificcontextswheretheyareused.

View arXiv pageView PDFProject pageGitHubAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.16679 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.16679 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.16679 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

AI for Games in the Foundation Model Era

arXiv cs.AI

This survey paper organizes AI applications in games into six roles based on foundation models, discussing transferability and evaluation challenges across the game lifecycle.

On the use of foundation models in cognitive science

arXiv cs.CL

This perspective paper from arXiv articulates a four-stage inferential framework for evaluating foundation models as cognitive and developmental models, emphasizing that behavioral alignment alone is insufficient and must be embedded within theoretical commitments and contrastive evaluation.

AI Native Games: A Survey and Roadmap

arXiv cs.AI

This survey paper defines AI-native games as those where runtime generative AI is constitutive of the core game loop, proposes a dual-axis G/N taxonomy, analyzes 53 games, and provides a roadmap for controllable generation, multimodal systems, and AI safety in game design.

Audio-Visual Intelligence in Large Foundation Models

Hugging Face Daily Papers

This survey paper provides a comprehensive review of audio-visual intelligence within large foundation models, establishing a unified taxonomy, synthesizing core methodologies, and outlining key datasets, benchmarks, and open research challenges.

AI fundamentals

OpenAI Blog

OpenAI Academy publishes an educational guide on AI fundamentals covering the landscape of AI systems, large language models, training stages (pre-training and post-training), and how to choose the right AI tools for different tasks.