# Static Analysis as a Feedback Loop: Enhancing LLM-Generated Code Beyond Correctness

arXiv: https://arxiv.org/abs/2508.14419 · HTML: https://mlsanity.com/paper/2508.14419/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2025.

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

- [Adaptive Hierarchical Evaluation of LLMs and SAST tools for CWE Prediction in Python](https://mlsanity.com/paper/2601.01320/) (2026)
- [Detecting and Correcting Hallucinations in LLM-Generated Code via Deterministic AST Analysis](https://mlsanity.com/paper/2601.19106/) (2026)
- [Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring](https://mlsanity.com/paper/2605.00754/) (2026)
- [Enhancing Debugging Skills with AI-Powered Assistance: A Real-Time Tool for Debugging Support](https://mlsanity.com/paper/2601.02504/) (2026)
- [Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy](https://mlsanity.com/paper/2607.21677/) (2026)
- [Characterizing the Quality Profile of AI-Generated C++ in Production](https://mlsanity.com/paper/2608.06640/) (2026)
- [What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code](https://mlsanity.com/paper/2609.12708/) (2026)
- [LintEval: Benchmarking LLMs on Linter-Guided File Refactoring](https://mlsanity.com/paper/2610.20027/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated impressive capabilities in code generation, achieving high scores on benchmarks such as HumanEval and MBPP. However, these benchmarks primarily assess functional correctness and neglect broader dimensions of code quality, including security, reliability, readability, and maintainability. In this work, we systematically evaluate the ability of LLMs to generate high-quality code across multiple dimensions using the PythonSecurityEval benchmark. We introduce an iterative static analysis-driven prompting algorithm that leverages Bandit and Pylint to identify and resolve code quality issues. Our experiments with GPT-4o show substantial improvements: security issues reduced from >40% to 13%, readability violations from >80% to 11%, and reliability warnings from >50% to 11% within ten iterations. These results demonstrate that LLMs, when guided by static analysis feedback, can significantly enhance code quality beyond functional correctness.