# Intermediate Languages Matter: Formal Choice Drives Neurosymbolic LLM Reasoning

arXiv: https://arxiv.org/abs/2502.17216 · HTML: https://mlsanity.com/paper/2502.17216/

## 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 2 of its 36 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Placed in

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

## Builds on (most cited first, 2 of 2)

- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Autoformalization with Large Language Models](https://mlsanity.com/paper/2205.12615/) (2022)

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

- [A Reality Check of Language Models as Formalizers on Constraint Satisfaction Problems](https://mlsanity.com/paper/2505.13252/) (2025)
- [Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning](https://mlsanity.com/paper/2509.04083/) (2025)
- [When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning](https://mlsanity.com/paper/2606.29354/) (2026)

## Abstract (arXiv)

Large language models (LLMs) achieve astonishing results on a wide range of tasks. However, their formal reasoning ability still lags behind. A promising approach is Neurosymbolic LLM reasoning. It works by using LLMs as translators from natural to formal languages and symbolic solvers for deriving correct results. Still, it remains unclear what the contributing factors to the success of Neurosymbolic LLM reasoning are. This paper shows that one important factor is the choice of the formal language. By comparing 4 formal languages on 3 datasets over 6 LLMs, we show that the choice of formal language affects both the syntactic and the semantic reasoning capability. Thereby, we introduce the intermediate language challenge, which is the challenge of picking a suitable formal language for neurosymbolic reasoning. Further, we compare the effects of using different in-context-learning examples in an ablation study. We conclude that on average, context-aware encodings help LLMs to reason, while there is no apparent effect of using comments or markdown syntax.