# SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation

arXiv: https://arxiv.org/abs/2510.25975 · HTML: https://mlsanity.com/paper/2510.25975/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Mathematical reasoning, one of 17 directions in LLM reasoning.
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 29 Oct 2025.

## Placed in

- LLM reasoning / [Mathematical reasoning](https://mlsanity.com/lr/mathematical-reasoning/)

## Builds on (most cited first, 10 of 10)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning](https://mlsanity.com/paper/2402.17231/) (2024)

## Built on by (most cited first, 4 of 4)

- [LLMs with in-context learning for Algorithmic Theoretical Physics](https://mlsanity.com/paper/2605.08212/) (2026)
- [TheoremForge: Scaling up Formal Data Synthesis with Low-Budget Agentic Workflow](https://mlsanity.com/paper/2601.17332/) (2026)
- [From Policy to Logic for Efficient and Interpretable Coverage Assessment](https://mlsanity.com/paper/2601.01266/) (2026)
- [Signals Are Not States: Neuro-Symbolic Safeguards for Culturally Aware Classroom AI](https://mlsanity.com/paper/2603.22793/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) often struggle with complex mathematical reasoning, where prose-based generation leads to unverified and arithmetically unsound solutions. Current prompting strategies like Chain of Thought still operate within this unreliable medium, lacking a mechanism for deterministic verification. To address these limitations, we introduce SymCode, a neurosymbolic framework that reframes mathematical problem-solving as a task of verifiable code generation using the SymPy library. We evaluate SymCode on challenging benchmarks, including MATH-500 and OlympiadBench, demonstrating significant accuracy improvements of up to 13.6 percentage points over baselines. Our analysis shows that SymCode is not only more token-efficient but also fundamentally shifts model failures from opaque logical fallacies towards transparent, programmatic errors. By grounding LLM reasoning in a deterministic symbolic engine, SymCode represents a key step towards more accurate and trustworthy AI in formal domains.