GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yuchen, Lin, Cong, Nasir, Muhammad Umair, Bontrager, Philip, Liu, Jialin, Togelius, Julian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910224111108096
author Li, Yuchen
Lin, Cong
Nasir, Muhammad Umair
Bontrager, Philip
Liu, Jialin
Togelius, Julian
author_facet Li, Yuchen
Lin, Cong
Nasir, Muhammad Umair
Bontrager, Philip
Liu, Jialin
Togelius, Julian
contents We introduce GVGAI-LLM, a video game benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). Built on the General Video Game AI framework, it features a diverse collection of arcade-style games designed to test a model's ability to handle tasks that differ from most existing LLM benchmarks. The benchmark leverages a video game description language that enables the rapid creation of new games (including rules and levels), helping to prevent overfitting over time. Each game scene is represented by a compact set of ASCII characters, allowing for efficient processing by language models. GVGAI-LLM defines interpretable metrics, including meaningful step ratio, step efficiency, and overall score, to assess model behavior. Through zero-shot evaluations across 118 games with diverse challenges and skill depth, we reveal persistent limitations of LLMs in spatial reasoning and basic planning. Current models consistently exhibit spatial and logical errors, motivating structured prompting and spatial grounding techniques. Although these interventions lead to partial improvements, the benchmark remains very far from being solved. GVGAI-LLM serves as a reproducible testbed for advancing research on language model capabilities, with a particular emphasis on agentic behavior and spatial reasoning. Furthermore, its ability to generate infinite benchmarks, both manually and procedurally, provides a scalable framework for longitudinal evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08501
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games
Li, Yuchen
Lin, Cong
Nasir, Muhammad Umair
Bontrager, Philip
Liu, Jialin
Togelius, Julian
Artificial Intelligence
We introduce GVGAI-LLM, a video game benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). Built on the General Video Game AI framework, it features a diverse collection of arcade-style games designed to test a model's ability to handle tasks that differ from most existing LLM benchmarks. The benchmark leverages a video game description language that enables the rapid creation of new games (including rules and levels), helping to prevent overfitting over time. Each game scene is represented by a compact set of ASCII characters, allowing for efficient processing by language models. GVGAI-LLM defines interpretable metrics, including meaningful step ratio, step efficiency, and overall score, to assess model behavior. Through zero-shot evaluations across 118 games with diverse challenges and skill depth, we reveal persistent limitations of LLMs in spatial reasoning and basic planning. Current models consistently exhibit spatial and logical errors, motivating structured prompting and spatial grounding techniques. Although these interventions lead to partial improvements, the benchmark remains very far from being solved. GVGAI-LLM serves as a reproducible testbed for advancing research on language model capabilities, with a particular emphasis on agentic behavior and spatial reasoning. Furthermore, its ability to generate infinite benchmarks, both manually and procedurally, provides a scalable framework for longitudinal evaluation.
title GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games
topic Artificial Intelligence
url https://arxiv.org/abs/2508.08501