# Hallucination Stations: On Some Basic Limitations of Transformer-Based Language Models

arXiv: https://arxiv.org/abs/2507.07505 · HTML: https://mlsanity.com/paper/2507.07505/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 10 Jul 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [On The Computational Complexity of Self-Attention](https://mlsanity.com/paper/2209.04881/) (2022)
- [Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2](https://mlsanity.com/paper/2502.03544/) (2025)
- [A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions](https://mlsanity.com/paper/2501.16150/) (2025)

## Built on by (most cited first, 2 of 2)

- [Secure and Efficient Access Control for Computer-Use Agents via Context Space](https://mlsanity.com/paper/2509.22256/) (2025)
- [Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost](https://mlsanity.com/paper/2609.39358/) (2026)

## Abstract (arXiv)

In this paper we explore hallucinations and related capability limitations in LLMs and LLM-based agents from the perspective of computational complexity. We show that beyond a certain complexity, LLMs are incapable of carrying out computational and agentic tasks or verifying their accuracy.