一句话：提出 SymGPT，用大语言模型把 ERC 规则翻译为 DSL 并由符号执行自动检测智能合约违规。
本文关注智能合约对 ERC 标准的合规性验证问题。作者首先对三大 ERC 标准中的 132 条规则进行实证分析，考察其内容、安全影响与自然语言描述特征。基于该研究，SymGPT 让大语言模型将 ERC 规则翻译为领域特定语言，再根据翻译结果合成约束以刻画可能的规则违反行为，最后通过符号执行检测违规。在 4,000 个真实合约上，SymGPT 共发现 5,783 处 ERC 规则违规，其中 1,375 处具有可用于资金窃取的明确攻击路径。与六种自动化技术和一项安全专家审计服务相比，SymGPT 均表现更优，表明其在智能合约分析上具有显著优势。
This paper introduces SymGPT , a tool that combines LLMs with symbolic execution to automatically verify smart contracts’ compliance with ERC rules. We begin by empirically analyzing 132 ERC rules from three major ERC standards, examining their content, security implications, and natural language descriptions. Based on this study, SymGPT instructs an LLM to translate ERC rules into a domain-specific language, synthesizes constraints from the translated rules to model potential rule violations, and performs symbolic execution for violation detection. Our evaluation shows that SymGPT identifies 5,783 ERC rule violations in 4,000 real-world contracts, including 1,375 violations with clear attack paths for financial theft. Furthermore, SymGPT outperforms six automated techniques and a security-expert auditing service, underscoring its superiority over current smart contract analysis methods.
@article{paperbot3850,
title = {SymGPT: Auditing Smart Contracts via Combining Symbolic Execution with Large Language Models},
author = {Shihao Xia and Mengting He and Shuai Shao and Tingting Yu and Yiying Zhang and Nobuko Yoshida and Linhai Song},
journal = {Proceedings of the ACM on Programming Languages},
volume = {10},
number = {OOPSLA1},
year = {2026},
doi = {10.1145/3798217}
}