2026-05-25T21:18:18Zhttps://keep.lib.asu.edu/oai/request

oai:keep.lib.asu.edu:node-2023182025-08-18T22:22:09Zoai_pmh:alloai_pmh:repo_items

202318 https://hdl.handle.net/2286/R.2.N.202318 http://rightsstatements.org/vocab/InC/1.0/ All Rights Reserved 2025 51 pages Masters Thesis Academic theses en Zhu, Samuel Jiarong Bao, Tiffany Shoshitaishvili, Yan Wang, Fish Arizona State University Partial requirement for: M.S., Arizona State University, 2025 Field of study: Computer Science Although symbolic execution is a powerful tool for vulnerability analysis, it is fre- quently hampered by the path explosion issue. Previous attempts to reduce the search space caused by path explosion have focused on pruning infeasible paths and comparing states. Machine learning has also been used to train a model to prune the search space of states. The rise of generalized Large Language Models (LLMs) provides an opportunity to avoid this cumbersome training process. LLMs have been shown to be very effective in the field of code analysis. This paper demonstrates a technique to use LLMs, paired with techniques derived from observing human ex- perts, in order to perform effective symbolic execution by using path selection. This paper creates a framework to integrate an LLM with a symbolic execution process and measures its effects compared to an existing symbolic execution engine, angr. The results show that the LLM performs equivalent to or better compared to existing methods when comparing the number of logical branches taken. By demonstrating this approach’s effectiveness, this paper opens an opportunity for further expansion of the usage of LLMs within symbolic execution. Computer Science Large Language Models Path Selection Symbolic Execution Leveraging Large Language Models and Expert Techniques for Path Selection