FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing
Yunlong Lyu, Peng Chen, Fengyi Wu, Junzhe Yu, Kit Long Hon, Hao Chen

TL;DR
FuzzAgent introduces a multi-agent evolutionary approach to library fuzzing, improving coverage and bug detection in C/C++ libraries by iteratively refining testing strategies based on runtime feedback.
Contribution
This work presents FuzzAgent, a novel multi-agent system that enhances library fuzzing through iterative, evidence-driven decision making, surpassing existing methods in coverage and bug discovery.
Findings
FuzzAgent achieves 45-92% higher branch coverage than baselines.
It identifies 102 genuine bugs, with 78 already fixed by maintainers.
The system operates fully automatically across 20 real-world libraries.
Abstract
Library fuzzing is essential for hardening the software supply chain, but adopting it at scale remains expensive. Practitioners still spend substantial effort on environment setup, struggle to generate harnesses that respect intricate API constraints, and lack reliable means to tell genuine library bugs from harness-induced crashes. Recent LLM-based systems automate parts of this pipeline, yet they typically operate as one-shot code generators that ignore runtime feedback, which limits both the depth of code they reach and the validity of the bugs they report. We argue that effective library fuzzing is iterative by nature: each campaign exposes new coverage bottlenecks and crashes, and the next campaign should evolve from these signals rather than restart from scratch. Building on this insight, we present FuzzAgent, a multi-agent system that turns library fuzzing into an evolutionary…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
