GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

• URL: http://arxiv.org/abs/2604.07429v1
• Date: Wed, 08 Apr 2026 17:49:03 GMT
• Title: GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
• Abstract summary: GameWorld is a benchmark for evaluation of Multimodal Large Language Model (MLLM) game agents in browser environments.<n>Two game agent interfaces are studied: (i) computer-use agents that directly emit keyboard and mouse controls, and (ii) generalist multimodal agents that act in a semantic action space.<n>Results across 18 model-interface pairs suggest that even the best performing agent is far from achieving human capabilities on video games.
• Score: 76.60994803070436
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Towards an embodied generalist for real-world interaction, Multimodal Large Language Model (MLLM) agents still suffer from challenging latency, sparse feedback, and irreversible mistakes. Video games offer an ideal testbed with rich visual observations and closed-loop interaction, demanding fine-grained perception, long-horizon planning, and precise control. However, systematically evaluating these capabilities is currently hindered by heterogeneous action interfaces and heuristic verification. To this end, we introduce GameWorld, a benchmark designed for standardized and verifiable evaluation of MLLMs as generalist game agents in browser environments. Two game agent interfaces are studied: (i) computer-use agents that directly emit keyboard and mouse controls, and (ii) generalist multimodal agents that act in a semantic action space via deterministic Semantic Action Parsing. GameWorld contains 34 diverse games and 170 tasks, each paired with state-verifiable metrics for outcome-based evaluation. The results across 18 model-interface pairs suggest that even the best performing agent is far from achieving human capabilities on video games. Extensive experiments of repeated full-benchmark reruns demonstrate the robustness of the benchmark, while further studies on real-time interaction, context-memory sensitivity, and action validity expose more challenges ahead for game agents. Together, by offering a standardized, verifiable, and reproducible evaluation framework, GameWorld lays a robust foundation for advancing research on multimodal game agents and beyond. The project page is at https://gameworld-bench.github.io.

Related papers

• PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives [86.3073067035531]
  Video world models simulate future states conditioned on current observations and user actions.<n>Recent systems have demonstrated impressive video consistency and action controllability over long sequences.<n>But fairly comparing these interactive models remains challenging.<n>We employ multi-modal Agent Players to interact with world models toward specified long-horizon objectives.
  arXiv  Detail & Related papers  (2026-08-13T17:59:30Z)
• GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine? [65.42976417627254]
  Game generation takes place within a game engine, where scripts, scenes, assets, rendering, and runtime interactions must jointly produce coherent gameplay.<n>We formalize end-to-end game generation as the problem of producing a complete game artifact.<n>We instantiate this framework as GameCraft-Bench, a benchmark comprising 140 Godot tasks across 15 game families.
  arXiv  Detail & Related papers  (2026-06-16T12:34:39Z)
• MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs [54.81359054218573]
  We introduce Mindgames, a multi-game arena and evaluation platform for large language models (LLMs)<n>Mindgames provides a unified interaction interface, TrueSkill-based rating, and full trajectory logging across four game environments.<n>We analyze 29,571 multi-agent games with turn-level observations, actions, and rewards, together with MG-Ref, a deterministic offline tournament protocol.
  arXiv  Detail & Related papers  (2026-05-28T07:33:47Z)
• GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents [4.920953895710103]
  We introduce GameplayQA, a framework for evaluating agentic-centric perception and reasoning through video understanding.<n>We densely annotate multiplayer 3D gameplay videos at 1.22 labels/second, with time-synced, concurrent captions of states, actions, and events structured around a triadic system of Self, Other Agents, and the World.<n>From these annotations, we refined 2.4K diagnostic QA pairs organized into three levels of cognitive complexity, accompanied by a structured distractor taxonomy.
  arXiv  Detail & Related papers  (2026-03-25T14:10:45Z)
• Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents [56.25101378553328]
  We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned keyboard-mouse inputs.<n>Game-TARS is pre-trained on over 500B tokens with diverse trajectories and multimodal data.<n> Experiments show that Game-TARS achieves about 2 times the success rate over the previous sota model on open-world Minecraft tasks.
  arXiv  Detail & Related papers  (2025-10-27T17:43:51Z)
• FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games [56.81554611870848]
  We introduce FlashAdventure, a benchmark of 34 Flash-based adventure games designed to test full story arc completion.<n>We also propose CUA-as-a-Judge, an automated gameplay evaluator, and COAST, an agentic framework leveraging long-term clue memory.<n> Experiments show current GUI agents struggle with full story arcs, while COAST improves milestone completion by bridging the observation-behavior gap.
  arXiv  Detail & Related papers  (2025-09-01T01:33:16Z)
• V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models [84.27290155010533]
  We introduce Vision-centric Multiple Abilities Game Evaluation (V-MAGE), a novel game-based evaluation framework.<n>V-MAGE features five distinct video games comprising over 30 carefully constructed evaluation scenarios.<n>We show V-MAGE provides actionable insights for improving the visual and reasoning capabilities of MLLMs in dynamic, interactive settings.
  arXiv  Detail & Related papers  (2025-04-08T15:43:01Z)
• A Survey on Large Language Model-Based Game Agents [35.34074811680046]
  Game agents offer a valuable testbed for exploring capabilities relevant to Artificial General Intelligence.<n>Recently, the emergence of Large Language Models (LLMs) provides new opportunities to endow these agents with generalizable reasoning.<n>This survey offers an up-to-date review of LLM-based game agents through a unified reference architecture.
  arXiv  Detail & Related papers  (2024-04-02T15:34:18Z)
• Preference-conditioned Pixel-based AI Agent For Game Testing [1.5059676044537105]
  Game-testing AI agents that learn by interaction with the environment have the potential to mitigate these challenges. This paper proposes an agent design that mainly depends on pixel-based state observations while exploring the environment conditioned on a user's preference. Our agent significantly outperforms state-of-the-art pixel-based game testing agents over exploration coverage and test execution quality when evaluated on a complex open-world environment resembling many aspects of real AAA games.
  arXiv  Detail & Related papers  (2023-08-18T04:19:36Z)
• An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games [79.23847247132345]
  This work investigates how well an artificial agent can benefit from playing guessing games when later asked to perform on novel NLP downstream tasks such as Visual Question Answering (VQA) We propose two ways to exploit playing guessing games: 1) a supervised learning scenario in which the agent learns to mimic successful guessing games and 2) a novel way for an agent to play by itself, called Self-play via Iterated Experience Learning (SPIEL)
  arXiv  Detail & Related papers  (2021-01-31T10:30:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.