# Orion: Fuzzing Workflow Automation

arXiv: https://arxiv.org/abs/2509.15195 · HTML: https://mlsanity.com/paper/2509.15195/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 49 references that are in the map.
- First posted on arXiv 18 Sep 2025.

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

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG](https://mlsanity.com/paper/2406.11147/) (2024)
- [Prompt Fuzzing for Fuzz Driver Generation](https://mlsanity.com/paper/2312.17677/) (2023)
- [KNighter: Transforming Static Analysis with LLM-Synthesized Checkers](https://mlsanity.com/paper/2503.09002/) (2025)
- [How Effective Are They? Exploring Large Language Model Based Fuzz Driver Generation](https://mlsanity.com/paper/2307.12469/) (2023)
- [ELFuzz: Efficient Input Generation via LLM-driven Synthesis Over Fuzzer Space](https://mlsanity.com/paper/2506.10323/) (2025)
- [SoK: Prudent Evaluation Practices for Fuzzing](https://mlsanity.com/paper/2405.10220/) (2024)
- [Fixing Security Vulnerabilities with AI in OSS-Fuzz](https://mlsanity.com/paper/2411.03346/) (2024)
- [Large Language Model assisted Hybrid Fuzzing](https://mlsanity.com/paper/2412.15931/) (2024)
- [SmartSeed: Smart Seed Generation for Efficient Fuzzing](https://mlsanity.com/paper/1807.02606/) (2018)
- [LibLMFuzz: LLM-Augmented Fuzz Target Generation for Black-box Libraries](https://mlsanity.com/paper/2507.15058/) (2025)
- [May the Feedback Be with You! Unlocking the Power of Feedback-Driven Deep Learning Framework Fuzzing via LLMs](https://mlsanity.com/paper/2506.17642/) (2025)

## Abstract (arXiv)

Fuzz testing is one of the most effective techniques for finding software vulnerabilities. While modern fuzzers can generate inputs and monitor executions automatically, the overall workflow, from analyzing a codebase, to configuring harnesses, to triaging results, still requires substantial manual effort. Prior attempts focused on single stages such as harness synthesis or input minimization, leaving researchers to manually connect the pieces into a complete fuzzing campaign. We introduce Orion, a framework that automates the the manual bottlenecks of fuzzing by integrating LLM reasoning with traditional tools, allowing campaigns to scale to settings where human effort alone was impractical. Orion uses LLMs for code reasoning and semantic guidance, while relying on deterministic tools for verification, iterative refinement, and tasks that require precision. Across our benchmark suite, Orion reduces human effort by 46-204x depending on the workflow stage, and we demonstrate its effectiveness through the discovery of two previously unknown vulnerabilities in the widely used open-source clib library.