{"ID":2848787,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.25975","arxiv_id":"2510.25975","title":"SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation","abstract":"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.","short_abstract":"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 a...","url_abs":"https://arxiv.org/abs/2510.25975","url_pdf":"https://arxiv.org/pdf/2510.25975v2","authors":"[\"Sina Bagheri Nezhad\",\"Yao Li\",\"Ameeta Agrawal\"]","published":"2025-10-29T21:17:57Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.PL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}