SCAFFOLD-CEGIS: Preventing Latent Security Degradation in LLM-Driven Iterative Code Refinement

Authors: Yi Chen, Yun Bian, Haiquan Wang, Shihao Li, Zhe Cui
Published: 2026-03-09

Source: https://arxiv.org/abs/2603.08520

PDF: https://arxiv.org/pdf/2603.08520

Labels Predicted by AI

LLM Performance Evaluation Program Analysis

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

The application of large language models to code generation has evolved from one-shot generation to iterative refinement, yet the evolution of security throughout iteration remains insufficiently understood. Through comparative experiments on three mainstream LLMs, this paper reveals the iterative refinement paradox: specification drift during multi-objective optimization causes security to degrade gradually over successive iterations. Taking GPT-4o as an example, 43.7