Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs

ACL ARR 2025 May Submission882 Authors

Abstract: Code and reasoning recently exhibit a mutually reinforcing relationship in large language models (LLMs): Code is abstract, modular, highly structured and has strong logic, guiding reasoning in training and inference. While reasoning translates high-level goals into small executable steps, enable more sophisticated code intellignece, solving real-world challenging software development problems. In this study, we examine how code serves as a structured medium for enhancing reasoning - providing verifiable execution paths, enforcing logical decomposition, and enabling runtime validation, and how advances in reasoning have transformed code intelligence from basic completion to sophisticated agent - enabling models to tackle complex software engineering tasks through deliberate planning and systematic debugging. Finally, we identify key challenges and propose future research directions may deepen the synergy, ultimately advancing LLM performance in both complex reasoning and code intelligence.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: NLP Applications,Language Modeling

Contribution Types: Surveys

Languages Studied: English,programming

Submission Number: 882