# LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning

arXiv: https://arxiv.org/abs/2507.15521 · HTML: https://mlsanity.com/paper/2507.15521/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 8 of 8)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020)
- [Language Models Meet World Models: Embodied Experiences Enhance Language Models](https://mlsanity.com/paper/2305.10626/) (2023)
- [Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning](https://mlsanity.com/paper/2312.05230/) (2023)
- [Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2402.08955/) (2024)
- [Adversarial Policies Beat Superhuman Go AIs](https://mlsanity.com/paper/2211.00241/) (2022)

## Abstract (arXiv)

Do large language models (LLMs) construct and manipulate internal world models, or do they rely solely on statistical associations represented as output layer token probabilities? We adapt cognitive science methodologies from human mental models research to test LLMs on pulley system problems using TikZ-rendered stimuli. Study 1 examines whether LLMs can estimate mechanical advantage (MA). State-of-the-art models performed marginally but significantly above chance, and their estimates correlated significantly with ground-truth MA. Significant correlations between number of pulleys and model estimates suggest that models employed a pulley counting heuristic, without necessarily simulating pulley systems to derive precise values. Study 2 tested this by probing whether LLMs represent global features crucial to MA estimation. Models evaluated a functionally connected pulley system against a fake system with randomly placed components. Without explicit cues, models identified the functional system as having greater MA with F1=0.8, suggesting LLMs could represent systems well enough to differentiate jumbled from functional systems. Study 3 built on this by asking LLMs to compare functional systems with matched systems which were connected up but which transferred no force to the weight; LLMs identified the functional system with F1=0.46, suggesting random guessing. Insofar as they may generalize, these findings are compatible with the notion that LLMs manipulate internal world models, sufficient to exploit statistical associations between pulley count and MA (Study 1), and to approximately represent system components' spatial relations (Study 2). However, they may lack the facility to reason over nuanced structural connectivity (Study 3). We conclude by advocating the utility of cognitive scientific methods to evaluate the world-modeling capacities of artificial intelligence systems.