# Large Language Model Guided Self-Debugging Code Generation

arXiv: https://arxiv.org/abs/2502.02928 · HTML: https://mlsanity.com/paper/2502.02928/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 5 Feb 2025.

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [Large Language Models for Software Engineering: Survey and Open Problems](https://mlsanity.com/paper/2310.03533/) (2023)
- [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024)
- [Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step](https://mlsanity.com/paper/2402.16906/) (2024)
- [Repair Is Nearly Generation: Multilingual Program Repair with LLMs](https://mlsanity.com/paper/2208.11640/) (2022)
- [CodeScore: Evaluating Code Generation by Learning Code Execution](https://mlsanity.com/paper/2301.09043/) (2023)
- [What's Wrong with Your Code Generated by Large Language Models? An Extensive Study](https://mlsanity.com/paper/2407.06153/) (2024)
- [CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation](https://mlsanity.com/paper/2308.08784/) (2023)
- [An Empirical Study on Usage and Perceptions of LLMs in a Software Engineering Project](https://mlsanity.com/paper/2401.16186/) (2024)
- [Large Language Models as Test Case Generators: Performance Evaluation and Enhancement](https://mlsanity.com/paper/2404.13340/) (2024)

## Built on by (most cited first, 8 of 8)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [SRLCG: Self-Rectified Large-Scale Code Generation with Multidimensional Chain-of-Thought and Dynamic Backtracking](https://mlsanity.com/paper/2504.00532/) (2025)
- [Adaptive Hierarchical Evaluation of LLMs and SAST tools for CWE Prediction in Python](https://mlsanity.com/paper/2601.01320/) (2026)
- [UPA: Unsupervised Prompt Agent via Tree-Based Search and Selection](https://mlsanity.com/paper/2601.23273/) (2026)
- [MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System](https://mlsanity.com/paper/2605.05949/) (2026)
- [Microskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation](https://mlsanity.com/paper/2606.05720/) (2026)
- [From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python](https://mlsanity.com/paper/2607.21069/) (2026)
- [MineValiCoder: Reliable Code Generation with Test Case Quality Mining and Bipartite Graph-Based Mutual Validation](https://mlsanity.com/paper/2607.22471/) (2026)

## Abstract (arXiv)

Automated code generation is gaining significant importance in intelligent computer programming and system deployment. However, current approaches often face challenges in computational efficiency and lack robust mechanisms for code parsing and error correction. In this work, we propose a novel framework, PyCapsule, with a simple yet effective two-agent pipeline and efficient self-debugging modules for Python code generation. PyCapsule features sophisticated prompt inference, iterative error handling, and case testing, ensuring high generation stability, safety, and correctness. Empirically, PyCapsule achieves up to 5.7% improvement of success rate on HumanEval, 10.3% on HumanEval-ET, and 24.4% on BigCodeBench compared to the state-of-art methods. We also observe a decrease in normalized success rate given more self-debugging attempts, potentially affected by limited and noisy error feedback in retention. PyCapsule demonstrates broader impacts on advancing lightweight and efficient code generation for artificial intelligence systems.