# SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing

arXiv: https://arxiv.org/abs/2511.12448 · HTML: https://mlsanity.com/paper/2511.12448/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 38 references that are in the map.
- First posted on arXiv 16 Nov 2025.

## Builds on (most cited first, 16 of 16)

- [The Art, Science, and Engineering of Fuzzing: A Survey](https://mlsanity.com/paper/1812.00140/) (2018)
- [Evaluating Fuzz Testing](https://mlsanity.com/paper/1808.09700/) (2018)
- [Learn&Fuzz: Machine Learning for Input Fuzzing](https://mlsanity.com/paper/1701.07232/) (2017)
- [Magma: A Ground-Truth Fuzzing Benchmark](https://mlsanity.com/paper/2009.01120/) (2020)
- [Fuzzing BusyBox: Leveraging LLM and Crash Reuse for Embedded Bug Unearthing](https://mlsanity.com/paper/2403.03897/) (2024)
- [Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators](https://mlsanity.com/paper/2501.19282/) (2025)
- [A systematic review of fuzzing based on machine learning techniques](https://mlsanity.com/paper/1908.01262/) (2019)
- [SoK: Prudent Evaluation Practices for Fuzzing](https://mlsanity.com/paper/2405.10220/) (2024)
- [Harnessing Large Language Models for Seed Generation in Greybox Fuzzing](https://mlsanity.com/paper/2411.18143/) (2024)
- [A Review of Machine Learning Applications in Fuzzing](https://mlsanity.com/paper/1906.11133/) (2019)
- [SmartSeed: Smart Seed Generation for Efficient Fuzzing](https://mlsanity.com/paper/1807.02606/) (2018)
- [SyzRetrospector: A Large-Scale Retrospective Study of Syzbot](https://mlsanity.com/paper/2401.11642/) (2024)
- [BugsRepo: A Comprehensive Curated Dataset of Bug Reports, Comments and Contributors Information from Bugzilla](https://mlsanity.com/paper/2504.18806/) (2025)
- [Semantic Fuzzing with Zest](https://mlsanity.com/paper/1812.00078/) (2018)
- [Faster Fuzzing: Reinitialization with Deep Neural Models](https://mlsanity.com/paper/1711.02807/) (2017)
- [ISC4DGF: Enhancing Directed Grey-box Fuzzing with LLM-Driven Initial Seed Corpus Generation](https://mlsanity.com/paper/2409.14329/) (2024)

## Built on by (most cited first, 1 of 1)

- [Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications](https://mlsanity.com/paper/2605.24883/) (2026)

## Abstract (arXiv)

We introduce SeedAIchemy, an automated LLM-driven corpus generation tool that makes it easier for developers to implement fuzzing effectively. SeedAIchemy consists of five modules which implement different approaches at collecting publicly available files from the internet. Four of the five modules use large language model (LLM) workflows to construct search terms designed to maximize corpus quality. Corpora generated by SeedAIchemy perform significantly better than a naive corpus and similarly to a manually-curated corpus on a diverse range of target programs and libraries.