# Coverage-Guided Multi-Agent Harness Generation for Java Library Fuzzing

arXiv: https://arxiv.org/abs/2603.08616 · HTML: https://mlsanity.com/paper/2603.08616/

## 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 5 of its 27 references that are in the map.
- First posted on arXiv 9 Mar 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, 5 of 5)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Prompt Fuzzing for Fuzz Driver Generation](https://mlsanity.com/paper/2312.17677/) (2023)
- [How Effective Are They? Exploring Large Language Model Based Fuzz Driver Generation](https://mlsanity.com/paper/2307.12469/) (2023)
- [When Fuzzing Meets LLMs: Challenges and Opportunities](https://mlsanity.com/paper/2404.16297/) (2024)

## Abstract (arXiv)

Coverage-guided fuzzing has proven effective for software testing, but targeting library code requires specialized fuzz harnesses that translate fuzzer-generated inputs into valid API invocations. Manual harness creation is time-consuming and requires deep understanding of API semantics, initialization sequences, and exception handling contracts. We present a multi-agent architecture that automates fuzz harness generation for Java libraries through specialized LLM-powered agents. Five ReAct agents decompose the workflow into research, synthesis, compilation repair, coverage analysis, and refinement. Rather than preprocessing entire codebases, agents query documentation, source code, and callgraph information on demand through the Model Context Protocol, maintaining focused context while exploring complex dependencies. To enable effective refinement, we introduce method-targeted coverage that tracks coverage only during target method execution to isolate target behavior, and agent-guided termination that examines uncovered source code to distinguish productive refinement opportunities from diminishing returns. We evaluated our approach on seven target methods from six widely-deployed Java libraries totaling 115,000+ Maven dependents. Our generated harnesses achieve a median 26% improvement over OSS-Fuzz baselines and outperform Jazzer AutoFuzz by 5% in package-scope coverage. Generation costs average 3.20 and 10 minutes per harness, making the approach practical for continuous fuzzing workflows. During a 12-hour fuzzing campaign, our generated harnesses discovered 3 bugs in projects that are already integrated into OSS-Fuzz, demonstrating the effectiveness of the generated harnesses.