Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development
Summary
Game2Player introduces a co-development loop where Builder, Coding Player, and VLM Player agents adapt web games, define verifiable tasks, and collect 15.7K gameplay trajectories to train visual agents, with Game2Player-9B substantially improving progress on PlayerBench and GameWorld benchmarks.
View Cached Full Text
Cached at: 11/19/26, 07:28 AM
Paper page - Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development
Source: https://huggingface.co/papers/2611.24154 Published on Nov 18
#3 Paper of the day Authors:
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
Gamesarearichtestbedforvisualagents,demandingperception,long-horizonplanning,andprecisecontrol.However,collectinghumangameplayiscostly,andlearningfromgameplayvideosrequiresinferringmissingactions.Existingdatasetsalsocoveralimitedrangeofgames,oftenwithoutexplicittasksorverifiableoutcomes.Toaddressthesegaps,weintroduceGame2Player,aframeworkthatco-developsgameenvironmentsandplayerstocollectdiverseandverifiablegameplayexperienceatscale.IntheGame2Playerloop,aBuilderagentadaptsexistingwebgames,exposestheirinternalstate,anddefinestaskswithstate-basedprogressmeasuresandsuccesschecks.ACodingPlayerandaVLMPlayerthenattemptthetasksandreportproblemstotheBuilderforrepair,sothatplayservesasbothenvironmentvalidationandtrainingdatacollection.WithGame2Player,webuild568verifiedwebgameswith3,436tasks,collect15.7Ktrajectories(307hoursofgameplay),andholdout50gamesasthebenchmarkPlayerBench.Toevaluatethecollectedexperienceastrainingdata,wetrainVLMagentswithprogress-weightedSFT,assigninggreaterweighttostepsthatadvancetaskprogress.Game2Player-9Bimprovesprogressfrom14.3%to31.2%onPlayerBenchandfrom30.0%to53.1%ontheexternalGameWorldbenchmark.Morebroadly,ourworksuggestsapathforvisualagentstoscaletheirgameplayexperiencebybuilding,verifying,andlearningfromexistinggameworlds.
View arXiv pageView PDFProject pageGitHub21Add to collection
Models citing this paper2
#### game2player/Game2Player-9B Image-Text-to-Text• 9B• Updatedabout 4 hours ago • 126 • 3
#### game2player/Game2Player-4B Image-Text-to-Text• 5B• Updatedabout 4 hours ago • 112 • 1
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2611.24154 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2611.24154 in a Space README.md to link it from this page.
Collections including this paper1
Similar Articles
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
PlayWorld is a benchmark for evaluating interactive video world models using multi-modal agent players pursuing long-horizon objectives. It assesses geometry consistency, interaction fidelity, and state evolution, revealing that current models struggle with spatial consistency and persistent state evolution.
Code2Games: Enabling Coding Agents for Gaming World Generation
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.
AgentGarten: Code Worlds for Evolving Agents
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.
PlayCraft: Designing Engaging Games from Agent Play Experience
PlayCraft is an automated framework that alternates a vision-based player agent's gameplay with a crafter agent's revisions to improve game mastery, yielding larger learning gains and steeper learning slopes across intelligence settings compared to initial games and baselines.
GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets
The paper presents GameGo, a scalable framework that transforms brief game seeds into full Product Requirements Documents and builds GameGoData (55,060 development trajectories) and GameGoBench (124 game queries) for training GameGoCoder, a coding agent that matches frontier models on game-development benchmarks.