SymGPT: auditing smart contracts via combining symbolic execution with large language models

Conference item

To govern smart contracts running on Ethereum, multiple Ethereum Request for Comment (ERC) standards have been developed, each defining a set of rules governing contract behavior. Violating these rules can cause serious security issues and financial losses, signifying the importance of verifying ERC compliance. Today’s practices of such verification include manual audits, expert-developed program-analysis tools, and large language models (LLMs), all of which remain ineffective at detecting ERC rule violations. 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.

Authors: Xia, S; He, M; Shao, S; Yu, T; Zhang, Y

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Association for Computing Machinery
• Journal: Proceedings of the ACM on Programming Languages More from this journal
• Volume: 10
• Article number: 109
• Publication date: 2026-04-10
• Acceptance date: 2025-12-17
• Event title: OOPSLA 2026
• Event location: Oakland, California, United States
• Event website: https://2026.splashcon.org/track/oopsla-2026
• Event start date: 2026-10-03
• Event end date: 2026-10-09
• DOI: 10.1145/3798217
• EISSN: 2475-1421
• Language: English
• Keywords: large language models; smart contracts; symbolic execution