# Why LLMs Cannot Think and How to Fix It

arXiv: https://arxiv.org/abs/2503.09211 · HTML: https://mlsanity.com/paper/2503.09211/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 0 of its 11 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Built on by (most cited first, 3 of 3)

- [Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction](https://mlsanity.com/paper/2504.15266/) (2025)
- [Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI](https://mlsanity.com/paper/2509.13345/) (2025)
- [Same Input, Different Scores: A Multi Model Study on the Inconsistency of LLM Judge](https://mlsanity.com/paper/2603.04417/) (2026)

## Abstract (arXiv)

This paper elucidates that current state-of-the-art Large Language Models (LLMs) are fundamentally incapable of making decisions or developing "thoughts" within the feature space due to their architectural constraints. We establish a definition of "thought" that encompasses traditional understandings of that term and adapt it for application to LLMs. We demonstrate that the architectural design and language modeling training methodology of contemporary LLMs inherently preclude them from engaging in genuine thought processes. Our primary focus is on this theoretical realization rather than practical insights derived from experimental data. Finally, we propose solutions to enable thought processes within the feature space and discuss the broader implications of these architectural modifications.