AGI Maze as a Benchmark Framework for World-Modeling Agents

arXiv 2026 30.9 benchmark, system

TLDR

Introduces AGI Maze, a benchmark for evaluating world-modeling in LLMs via grid-based mazes requiring memory and hidden state representation.

Reasoning

The paper presents a novel benchmark framework for testing world-modeling capabilities, with clear methodology and initial results showing LLM limitations. However, it lacks real-world experiments and the baseline agent evaluation is preliminary, limiting generalizability.

Read-first score

Read-first score 30.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 26.

Recency 6%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 18%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=baseline,benchmark,evaluation

Topical relevance 29%

37.1

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Citation impact 18%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 12%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 112.

Keyword Scores

world model

interactive world model

world dynamics prediction

world simulator

model-based reinforcement learning world model

generative world model

video world model

Resources

Paper