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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Nezhad, Sina Bagheri, Li, Yao, Agrawal, Ameeta
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914276345643008
author Nezhad, Sina Bagheri
Li, Yao
Agrawal, Ameeta
author_facet Nezhad, Sina Bagheri
Li, Yao
Agrawal, Ameeta
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25975
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation
Nezhad, Sina Bagheri
Li, Yao
Agrawal, Ameeta
Computation and Language
Programming Languages
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.
title SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation
topic Computation and Language
Programming Languages
url https://arxiv.org/abs/2510.25975