Thinking More, Harnessing Better: State Machine Guided Harness Automatic Generation with Project Digestion and Workflow Decomposition

• URL: http://arxiv.org/abs/2607.07007v1
• Date: Wed, 08 Jul 2026 05:04:28 GMT
• Title: Thinking More, Harnessing Better: State Machine Guided Harness Automatic Generation with Project Digestion and Workflow Decomposition
• Abstract summary: We present SynapseFlow, an automatic harness generator that addresses limitations through two key innovations.<n> SynapseFlow first analyzes source code to construct Structural Flow Graphs and extract coherent Function Triplets.<n>It then synthesizes harnesses via a four-stage process governed by a staged rollback algorithm to ensure correctness.
• Score: 16.37262243889993
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-quality fuzz harnesses are essential for effective gray-box fuzzing. While Large Language Models (LLMs) offer promise for automating this task, existing one-turn generation methods suffer from hallucinations and inadequate coverage due to coarse-grained function targeting and misaligned generation workflows. We present SynapseFlow, an automatic harness generator that addresses these limitations through two key innovations: dataflow-aware function aggregation and a staged, rollback-enabled generation workflow decomposition. SynapseFlow first analyzes source code to construct Structural Flow Graphs and extract coherent Function Triplets. It then synthesizes harnesses via a decomposed four-stage process governed by a staged rollback algorithm to ensure correctness. We evaluated SynapseFlow on 25 real-world open-source software projects. The experimental results indicate that SynapseFlow outperforms state-of-the-art tools (OSS-Fuzz-Gen, CKGFuzzer, PromeFuzz), achieving 3.07$\times$, 1.71$\times$, and 4.26$\times$ higher branch coverage, and 1.77$\times$, 1.51$\times$, and 1.36$\times$ higher bug detection rates, respectively. Most importantly, SynapseFlow discovered 7 previously unreported bugs (5 assigned CVEs), demonstrating its practical effectiveness in real-world bug discovery.

Related papers

• All in One: Generative Modeling as Mean-Field Game Design [9.305417960678357]
  Mean-field games (MFGs) offer a unifying lens on continuous-time generative modeling.<n>We develop an open-source library whose primary API is the cost, all twelve models are specified by four composable cost functions, and the training loop, log-Jacobian, and reverse-ODE sampler are shared automatically.<n>We additionally propose DI-Flow, a novel cost functional to encourage mode coverage, and provide learning-based solvers that substantially outperform neural training on MFG-dynamics rows.
  arXiv  Detail & Related papers  (2026-07-25T03:57:31Z)
• Scaling Laws for Agent Harnesses via Effective Feedback Compute [53.68149869349268]
  emphEffective Feedback Compute (EFC) is a trace-level scaling coordinate that credits feedback only when it is informative, valid, non-redundant, and retained for subsequent decisions.<n>EFC-based coordinates consistently predict failure rates better than raw-compute baselines.
  arXiv  Detail & Related papers  (2026-05-28T09:45:47Z)
• Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors [51.95306551061392]
  Automated agentic workflow design currently relies on per-task iterative search.<n>We present SWIFT, a framework that amortizes workflow design into reusable structural priors.<n> SWIFT outperforms the state-of-the-art search-based method on five benchmarks.
  arXiv  Detail & Related papers  (2026-04-27T21:25:00Z)
• Efficient Hybrid SE(3)-Equivariant Visuomotor Flow Policy via Spherical Harmonics for Robot Manipulation [51.48086451600577]
  E3Flow is a novel framework that addresses the limitations of equivariant diffusion policies.<n>It unifies efficient rectified flow with stable, multi-modal equivariant learning for the first time.<n>E3Flow achieves a 3.12% improvement in average success rate over the state-of-the-art Spherical Diffusion Policy.
  arXiv  Detail & Related papers  (2026-03-24T14:00:36Z)
• SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows [37.7899995917052]
  We find a way to fix the variance (which would otherwise be predicted by the VAE encoder) to a constant.<n>On the ImageNet $256 times 256$ generation task, our model SimFlow obtains a gFID score of 2.15, outperforming the state-of-the-art method STARFlow (gFID 2.40).<n>SimFlow can be seamlessly integrated with the end-to-end representation alignment (REPA-E) method and achieves an improved gFID of 1.91, setting a new state of the art among NFs.
  arXiv  Detail & Related papers  (2025-12-03T18:59:57Z)
• AlphaFlow: Understanding and Improving MeanFlow Models [74.64465762009475]
  We show that the MeanFlow objective naturally decomposes into two parts: trajectory flow matching and trajectory consistency.<n>Motivated by these insights, we introduce $alpha$-Flow, a broad family of objectives that unifies trajectory flow matching, Shortcut Model, and MeanFlow.<n>When trained from scratch on class-conditional ImageNet-1K 256x256 with vanilla DiT backbones, $alpha$-Flow consistently outperforms MeanFlow across scales and settings.
  arXiv  Detail & Related papers  (2025-10-23T17:45:06Z)
• FlowTS: Time Series Generation via Rectified Flow [67.41208519939626]
  FlowTS is an ODE-based model that leverages rectified flow with straight-line transport in probability space.<n>For unconditional setting, FlowTS achieves state-of-the-art performance, with context FID scores of 0.019 and 0.011 on Stock and ETTh datasets.<n>For conditional setting, we have achieved superior performance in solar forecasting.
  arXiv  Detail & Related papers  (2024-11-12T03:03:23Z)
• AFlow: Automating Agentic Workflow Generation [36.61172223528231]
  Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains.<n>We introduce AFlow, an automated framework that efficiently explores this space using Monte Carlo Tree Search.<n> Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-10-14T17:40:40Z)
• Simple ReFlow: Improved Techniques for Fast Flow Models [68.32300636049008]
  Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps. We propose seven improvements for training dynamics, learning and inference. We achieve state-of-the-art FID scores (without / with guidance, resp.) for fast generation via neural ODEs.
  arXiv  Detail & Related papers  (2024-10-10T11:00:55Z)
• Convergence analysis of OT-Flow for sample generation [7.416150473911164]
  Deep generative models aim to learn the underlying distribution of data and generate new ones. Despite the diversity of generative models and their high-quality generation performance in practice, most of them lack rigorous theoretical convergence proofs. In this work, we aim to establish some convergence results for OT-Flow, one of the deep generative models.
  arXiv  Detail & Related papers  (2024-03-24T16:05:57Z)
• Towards Optimal Statistical Watermarking [95.46650092476372]
  We study statistical watermarking by formulating it as a hypothesis testing problem. Key to our formulation is a coupling of the output tokens and the rejection region. We characterize the Uniformly Most Powerful (UMP) watermark in the general hypothesis testing setting.
  arXiv  Detail & Related papers  (2023-12-13T06:57:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.