SymGPT: Auditing Smart Contracts via Combining Symbolic Execution with Large Language Models
Proceedings of the ACM on Programming Languages · 10.04.2026 · 10 (OOPSLA1) · 482-512
DOI: 10.1145/3798217 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Programming Languages, online erschienen am 10.04.2026. Verfasst von Shihao Xia und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 137 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Engineering and Physical Sciences Research Council, HORIZON EUROPE Digital, Industry and Space, NSF.
Abstract (Originalsprache)
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.
Förderung
- Engineering and Physical Sciences Research Council
- HORIZON EUROPE Digital, Industry and Space
- NSF
- National Natural Science Foundation of China
Zitieren
APA
Xia, S., He, M., Shao, S., Yu, T., Zhang, Y., Yoshida, N., & Song, L. (2026). SymGPT: Auditing Smart Contracts via Combining Symbolic Execution with Large Language Models. Proceedings of the ACM on Programming Languages, 10(OOPSLA1), 482-512. https://doi.org/10.1145/3798217
Vancouver
Xia S, He M, Shao S, Yu T, Zhang Y, Yoshida N, et al. SymGPT: Auditing Smart Contracts via Combining Symbolic Execution with Large Language Models. Proceedings of the ACM on Programming Languages. 2026;10(OOPSLA1):482-512. doi:10.1145/3798217
BibTeX
@article{Xia2026,
author = {Xia, Shihao and He, Mengting and Shao, Shuai and Yu, Tingting and Zhang, Yiying and Yoshida, Nobuko and Song, Linhai},
title = {SymGPT: Auditing Smart Contracts via Combining Symbolic Execution with Large Language Models},
journal = {Proceedings of the ACM on Programming Languages},
year = {2026},
volume = {10},
number = {OOPSLA1},
pages = {482--512},
doi = {10.1145/3798217}
}
EUVIMED