mlsanityData to 14 Oct 2026

MSCoT: Structured Chain-of-Thought Generation for Multiple Programming Languages

arXiv 2504.10178 ↗First posted 14 Apr 2025cs.SEcited by 4

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

Abstract (arXiv)

With the rapid development of code intelligence, the application of multiple programming languages is becoming increasingly widespread. However, most existing code generation models mainly focus on a single or a few programming languages, resulting in unsatisfactory performance in a multilingual environment. Chain-of-Thought (CoT) reasoning can significantly improve the performance of the model without the need for retraining or fine-tuning the code generation model by reasonably decomposing complex code generation tasks into multiple subtasks and gradually deriving solutions for each subtask. Nevertheless, the existing CoT generation methods mainly concentrate on Python code, and the performance on other programming languages remains unclear. To fill this gap, we first constructed a CoT generation dataset for 12 programming languages through multi-agent technology. On this basis, we proposed a CoT generation method MSCoT applicable to multiple programming languages. By introducing CoT into the code generation large model, the performance of the code generation large model in a multilingual environment can be improved. Through large-scale empirical research, we compared the generalization abilities of MSCoT and the existing CoT generation methods on multiple programming languages and proved the effectiveness of MSCoT for multiple programming languages. In addition, we also designed a human study to prove the quality of the CoT generated by MSCoT. Finally, we opensourced the model and dataset of MSCoT to promote the research on CoT generation for multiple programming languages.

Key facts. Cited by 4 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 7 of its 43 references that are in the map. First posted on arXiv 14 Apr 2025.

Builds on

7 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Qwen2.5-Coder Technical Report18 Sep

Other references · 6

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  2. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
  3. 2024Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluationcited by 80
  4. 2023A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trendscited by 66
  5. 2024The Current Challenges of Software Engineering in the Era of Large Language Modelscited by 21
  6. 2024Less is More: Towards Green Code Large Language Models via Unified Structural Pruningcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025Code Reasoning for Software Engineering Tasks: A Survey and A Call to Actioncited by 4
  2. 2025GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generationcited by 3
  3. 2025Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generationcited by 2
  4. 2025Understanding Chain-of-Thought Effectiveness in Code Generation: An Empirical and Information-Theoretic Analysiscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2023Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models
  2. 2025SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning
  3. 2023Structured Chain-of-Thought Prompting for Code Generation
  4. 2024Assessing Code Generation with Intermediate Languages
  5. 2025Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
  6. 2025CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models
  7. 2024Markov Chain of Thought for Efficient Mathematical Reasoning
  8. 2026Hierarchical Chain-of-Thought: Enhancing LLM Reasoning Performance and Efficiency