# How Large Language Models Need Symbolism

arXiv: https://arxiv.org/abs/2509.21404 · HTML: https://mlsanity.com/paper/2509.21404/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 12 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 4 of 4)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2](https://mlsanity.com/paper/2502.03544/) (2025)
- [AutoSAT: Automatically Optimize SAT Solvers via Large Language Models](https://mlsanity.com/paper/2402.10705/) (2024)

## Built on by (most cited first, 1 of 1)

- [Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMs](https://mlsanity.com/paper/2603.14505/) (2026)

## Abstract (arXiv)

We argue that AI's future requires more than scaling. To unlock genuine discovery, large language models need a compass: human-crafted symbols to guide their powerful but blind intuition.