# Fuzzing with Agents? Generators Are All You Need

arXiv: https://arxiv.org/abs/2604.01442 · HTML: https://mlsanity.com/paper/2604.01442/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 62 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 24 of 24)

- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation](https://mlsanity.com/paper/2302.06527/) (2023)
- [Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?](https://mlsanity.com/paper/2511.13646/) (2025)
- [Automated Unit Test Improvement using Large Language Models at Meta](https://mlsanity.com/paper/2402.09171/) (2024)
- [The Art, Science, and Engineering of Fuzzing: A Survey](https://mlsanity.com/paper/1812.00140/) (2018)
- [Interactive Code Generation via Test-Driven User-Intent Formalization](https://mlsanity.com/paper/2208.05950/) (2022)
- [Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Code](https://mlsanity.com/paper/2206.01335/) (2022)
- [WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models](https://mlsanity.com/paper/2310.15991/) (2023)
- [Evaluating Fuzz Testing](https://mlsanity.com/paper/1808.09700/) (2018)
- [Can Large Language Models Write Good Property-Based Tests?](https://mlsanity.com/paper/2307.04346/) (2023)
- [CAT-LM: Training Language Models on Aligned Code And Tests](https://mlsanity.com/paper/2310.01602/) (2023)
- [Prompt Fuzzing for Fuzz Driver Generation](https://mlsanity.com/paper/2312.17677/) (2023)
- [FairFuzz: Targeting Rare Branches to Rapidly Increase Greybox Fuzz Testing Coverage](https://mlsanity.com/paper/1709.07101/) (2017)
- [Angora: Efficient Fuzzing by Principled Search](https://mlsanity.com/paper/1803.01307/) (2018)
- [ELFuzz: Efficient Input Generation via LLM-driven Synthesis Over Fuzzer Space](https://mlsanity.com/paper/2506.10323/) (2025)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Agentic Property-Based Testing: Finding Bugs Across the Python Ecosystem](https://mlsanity.com/paper/2510.09907/) (2025)
- [An Empirical Study of OSS-Fuzz Bugs](https://mlsanity.com/paper/2103.11518/) (2021)
- [DiffSpec: Differential Testing with LLMs using Natural Language Specifications and Code Artifacts](https://mlsanity.com/paper/2410.04249/) (2024)
- [BeDivFuzz: Integrating Behavioral Diversity into Generator-based Fuzzing](https://mlsanity.com/paper/2202.13114/) (2022)
- [Testing Database Engines via Query Plan Guidance](https://mlsanity.com/paper/2312.17510/) (2023)
- [Growing a Test Corpus with Bonsai Fuzzing](https://mlsanity.com/paper/2103.04388/) (2021)
- [Automatic, Expressive, and Scalable Fuzzing with Stitching](https://mlsanity.com/paper/2602.18689/) (2026)

## Abstract (arXiv)

Modern generator-based fuzzing techniques combine lightweight input generators with coverage-guided mutation as a method of exploring deep execution paths in a target program. A complimentary approach in prior research focuses on creating highly customized, domain-specific generators that encode structural and semantic logic sufficient enough to reach deep program states; the challenge comes from the overhead of writing and testing these complex generators. We investigate whether AI coding agents can automatically synthesize such target-specific generators, and whether the resulting generators are strong enough to obviate the need for coverage guidance and mutation entirely. Our approach, Gentoo, is comprised of an LLM coding agent (provided terminal access and source code of the fuzz target and its library) instructed to iteratively synthesize and refine an input generator, and optionally provided fine-grained predicate-level coverage feedback. We evaluate three configurations of Gentoo against human-written generators on fuzz targets for 7 real-world Java libraries. Our findings show that agent-synthesized generators achieve statistically significantly higher branch coverage than human-written baseline generators on 4 of 7 benchmarks. Critically, the use of coverage guidance and mutation strategies is not statistically significantly beneficial for agent-synthesized generators, but is significant for all human-written generators, suggesting that structural and semantic logic encoded in the agent generators makes coverage guidance largely unnecessary.