mlsanityData to 14 Oct 2026

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

arXiv 2502.19411 ↗First posted 26 Feb 2025cs.CL cs.AI cs.LGcited by 47

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

In large language models (LLMs), code and reasoning reinforce each other: code offers an abstract, modular, and logic-driven structure that supports reasoning, while reasoning translates high-level goals into smaller, executable steps that drive more advanced code intelligence. In this study, we examine how code serves as a structured medium for enhancing reasoning: it provides verifiable execution paths, enforces logical decomposition, and enables runtime validation. We also explore how improvements in reasoning have transformed code intelligence from basic completion to advanced capabilities, enabling models to address complex software engineering tasks through planning and debugging. Finally, we identify key challenges and propose future research directions to strengthen this synergy, ultimately improving LLM's performance in both areas.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 128 of its 161 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

128 of 161 references.

Closest ancestors · 18

Same direction, newest first

  1. 2024OpenAI o1 System Card21 Dec
  2. 2024What Makes Large Language Models Reason in (Multi-Turn) Code Generation?10 Oct
  3. 2024Steering Large Language Models between Code Execution and Textual Reasoning4 Oct
  4. 2024CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs2 Oct
  5. 2024Qwen2.5-Coder Technical Report18 Sep
  6. 2024SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning3 Jun
  7. 2024Learning to Reason via Program Generation, Emulation, and Search25 May
  8. 2024NExT: Teaching Large Language Models to Reason about Code Execution23 Apr
  9. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code12 Mar
  10. 2024OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement22 Feb
  11. 2024CodeMind: Evaluating Large Language Models for Code Reasoning15 Feb
  12. 2023Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models9 Dec
6 more
  1. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulator7 Dec
  2. 2023When Do Program-of-Thoughts Work for Reasoning?29 Aug
  3. 2023CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation17 Aug
  4. 2023Structured Chain-of-Thought Prompting for Code Generation11 May
  5. 2023Teaching Large Language Models to Self-Debug11 Apr
  6. 2022Reasoning Like Program Executors27 Jan

Other references · 110

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  8. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  9. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  10. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  11. 2021Program Synthesis with Large Language Modelscited by 3,637
  12. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
38 more
  1. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  2. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  3. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  4. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  5. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  6. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  7. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  8. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
  9. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  10. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 1,002
  11. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 903
  12. 2021Measuring Coding Challenge Competence With APPScited by 902
  13. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  14. 2023StarCoder: may the source be with you!cited by 799
  15. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 744
  16. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 740
  17. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 735
  18. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 733
  19. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  20. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 563
  21. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
  22. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 502
  23. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 498
  24. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 452
  25. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 421
  26. 2022A Systematic Evaluation of Large Language Models of Codecited by 363
  27. 2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 353
  28. 2024DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligencecited by 331
  29. 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Executioncited by 300
  30. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challengescited by 282
  31. 2024AutoCodeRover: Autonomous Program Improvementcited by 278
  32. 2023Self-collaboration Code Generation via ChatGPTcited by 258
  33. 2022Efficient Training of Language Models to Fill in the Middlecited by 255
  34. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 238
  35. 2020ReClor: A Reading Comprehension Dataset Requiring Logical Reasoningcited by 217
  36. 2024SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?cited by 203
  37. 2023LooGLE: Can Long-Context Language Models Understand Long Contexts?cited by 202
  38. 2023OctoPack: Instruction Tuning Code Large Language Modelscited by 189

50 most cited of 110 All 110 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 29; 2026: 18.

47 papers.

Sort:

By area:

  1. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondcited by 132
  2. 2025Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AIcited by 42
  3. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLcited by 38
  4. 2025VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Modelscited by 36
  5. 2025Safety Guardrails for LLM-Enabled Robotscited by 35
  6. 2025Mitigating Overthinking in Large Reasoning Models via Manifold Steeringcited by 33
  7. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarkscited by 33
  8. 2025Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoningcited by 21
  9. 2025DocAgent: A Multi-Agent System for Automated Code Documentation Generationcited by 18
  10. 2025Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learningcited by 17
  11. 2025QFFT, Question-Free Fine-Tuning for Adaptive Reasoningcited by 15
  12. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligencecited by 15
35 more
  1. 2025Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Modelscited by 13
  2. 2025Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulationcited by 11
  3. 2026HEARTS: Benchmarking LLM Reasoning on Health Time Seriescited by 11
  4. 2026Automatic Textbook Formalizationcited by 8
  5. 2025PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilitiescited by 7
  6. 2025Information Capacity: Evaluating the Efficiency of Large Language Models via Text Compressioncited by 7
  7. 2025Demystifying Errors in LLM Reasoning Traces: An Empirical Study of Code Execution Simulationcited by 5
  8. 2025Assessing the Impact of Code Changes on the Fault Localizability of Large Language Modelscited by 4
  9. 2025Code Reasoning for Software Engineering Tasks: A Survey and A Call to Actioncited by 4
  10. 2025Towards Verified Code Reasoning by LLMscited by 4
  11. 2025Evaluating Language Models' Evaluations of Gamescited by 4
  12. 2025Bye-bye, Bluebook? Automating Legal Drudgery With AI-Augmented Rule Followingcited by 3
  13. 2025Guideline Forest: Retrieval-Augmented Reasoning with Branching Experience-Induced Guidelinescited by 3
  14. 2026Sphinx: Benchmarking and Modeling for LLM-Driven Pull Request Reviewcited by 3
  15. 2026MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcementcited by 3
  16. 2026Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoningcited by 3
  17. 2025textttReMind: Understanding Deductive Code Reasoning in LLMscited by 2
  18. 2025An Empirical Study of Reasoning Steps in Thinking Code LLMscited by 2
  19. 2025Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generationcited by 1
  20. 2025Hound: Relation-First Knowledge Graphs for Complex-System Reasoning in Security Auditscited by 1
  21. 2026Not All Code Is Equal: A Data-Centric Study of Code Complexity and LLM Reasoningcited by 1
  22. 2026ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Modelscited by 1
  23. 2026D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discoverycited by 1
  24. 2026Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binariescited by 1
  25. 2026Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discoverycited by 1
  26. 2026Hi-TTRL: Regulating Consensus with Hints for Test-Time Reinforcement Learningcited by 1
  27. 2025Towards Reliable Multi-Agent Systems for Marketing Applications via Reflection, Memory, and Planningcited by 0
  28. 2025JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Modelscited by 0
  29. 2026The CompMath-MCQ Dataset: Are LLMs Ready for Higher-Level Math?cited by 0
  30. 2026Toward Executable Repository-Level Code Generation via Environment Alignmentcited by 0
  31. 2026NuHF Claw: A Risk Constrained Cognitive Agent Framework for Human Centered Procedure Support in Digital Nuclear Control Roomscited by 0
  32. 2026EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QAcited by 0
  33. 2026CogGuard: Cognitive and Operational Profiling for Proactive Warning in Edge Intelligent Servicescited by 0
  34. 2026Grounding AI Agents in Contracts: An Empirical Evaluation of Spec-Driven Test Generationcited by 0
  35. 2026VibeJam: A User Study Platform for Web Development with Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026CodeGlance: Understanding Code Reasoning Challenges in LLMs through Multi-Dimensional Feature Analysis
  2. 2025Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings
  3. 2025CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning
  4. 2025Dual-Process Scaffold Reasoning for Enhancing LLM Code Debugging
  5. 2025Breakpoint: Scalable evaluation of system-level reasoning in LLM code agents
  6. 2025A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models
  7. 2025Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment
  8. 2025On Code-Induced Reasoning in LLMs