{"ID":6138579,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-10T09:20:07.340435153Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.06619","arxiv_id":"2607.06619","title":"HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing","abstract":"Modern processor verification struggles to reach deep architectural states due to the inefficiencies of traditional mutation-based fuzzing. We propose HiFuzz, a novel hierarchical reinforcement learning framework that replaces mutation with a structured, two-layer generation process: a Program Agent for global layout and a Basic Block Agent for precise instruction filling. To overcome reward sparsity, HiFuzz integrates an adaptive coverage reward mechanism and a semantic-aware basic block encoder providing intrinsic feedback. Extensive evaluations on three real-world RISC-V cores demonstrate that HiFuzz significantly outperforms state-of-the-art fuzzers in coverage and bug detection.","short_abstract":"Modern processor verification struggles to reach deep architectural states due to the inefficiencies of traditional mutation-based fuzzing. We propose HiFuzz, a novel hierarchical reinforcement learning framework that replaces mutation with a structured, two-layer generation process: a Program Agent for global layout a...","url_abs":"https://arxiv.org/abs/2607.06619","url_pdf":"https://arxiv.org/pdf/2607.06619v1","authors":"[\"Ya Wang\",\"Hanwei Fan\",\"Zhenguo Liu\",\"Xiaofeng Zhou\",\"Yangdi Lyu\",\"Jiang Xu\",\"Wei Zhang\"]","published":"2026-07-07T09:27:30Z","proceeding":"cs.AR","tasks":"[\"cs.AR\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}