We present LISA, an agentic smart contract vulnerability detection framework that combines rule-based and logic-based methods to address a broad spectrum of vulnerabilities in smart contracts. LISA leverages data from historical audit reports to learn the detection experience (without model fine-tuning), enabling it to generalize learned patterns to unseen projects and evolving threat profiles. In our evaluation, LISA significantly outperforms both LLM-based approaches and traditional static analysis tools, achieving superior coverage of vulnerability types and higher detection accuracy. Our results suggest that LISA offers a compelling solution for industry: delivering more reliable and comprehensive vulnerability detection while reducing the dependence on manual effort.
Cite
@article{arxiv.2509.24698,
title = {LISA Technical Report: An Agentic Framework for Smart Contract Auditing},
author = {Izaiah Sun and Daniel Tan and Andy Deng},
journal= {arXiv preprint arXiv:2509.24698},
year = {2025}
}