PAGENT: Program Analysis Guided LLM Agent for Proof-of-Concept Generation
Open Access
- 1 October 2026
- journal article
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 2475-2497
Abstract
Software developers frequently receive vulnerability reports that require them to reproduce the vulnerability in a reliable manner by generating a proof-of-concept (PoC) input that triggers it. Given the source code for a software project and a specific code location for a potential vulnerability, automatically generating a PoC for the given vulnerability has been a challenging research problem. Symbolic execution and fuzzing techniques require expert guidance and manual steps and face scalability challenges for PoC generation. Although recent advances in LLMs have increased the level of automation and scalability, the success rate of PoC generation with LLMs remains quite low. In this paper, we present a novel approach called Program Analysis Guided proof of concept generation agENT (PAGENT) that is scalable and significantly improves the success rate of LLM-based automated PoC generation compared to prior results. PAGENT integrates lightweight and rule-based static analysis phases for providing static analysis guidance and sanitizer-based profiling and coverage information for providing dynamic analysis guidance with a PoC generation agent. Our experiments demonstrate that the resulting hybrid approach significantly outperforms the prior top-performing agentic approach by 132% for the PoC generation task across 10 open-source projects. PAGENT also discovered 32 post-patch PoCs that trigger the vulnerability in the patched version of the source code, with 2 reproducing the crash in the most recent versions.Keywords
All Related Versions
Funding Information
- Defense Sciences Office, DARPA (103238)
- National Science Foundation (2008660)
This publication has 40 references indexed in Scilit:
- Exploring Static Taint Analysis in LLMs: A Dynamic Benchmarking Framework for Measurement and Enhancement2025
- RepairAgent: An Autonomous, LLM-Based Agent for Program Repair2025
- Next-Generation Refactoring: Combining LLM Insights and IDE Capabilities for Extract Method2024
- Combining Static Analysis With Directed Symbolic Execution for Scalable and Accurate Memory Leak DetectionIEEE Access, 2024
- Practical Program Modularization with Type-Based Dependence Analysis2023
- Fuzzing: Challenges and ReflectionsIEEE Software, 2020
- An Efficient Greybox Fuzzing Scheme for Linux-based IoT Programs Through Binary Static Analysis2019
- Static Program Analysis as a Fuzzing Aid2017
- Static analysis of android apps: A systematic literature reviewInformation and Software Technology, 2017
- Soufflé: On Synthesis of Program Analyzers2016