{"ID":2894908,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.10338","arxiv_id":"2507.10338","title":"AssertCoder: LLM-Based Assertion Generation via Multimodal Specification Extraction","abstract":"Assertion-Based Verification (ABV) is critical for ensuring functional correctness in modern hardware systems. However, manually writing high-quality SVAs remains labor-intensive and error-prone. To bridge this gap, we propose AssertCoder, a novel unified framework that automatically generates high-quality SVAs directly from multimodal hardware design specifications. AssertCoder employs a modality-sensitive preprocessing to parse heterogeneous specification formats (text, tables, diagrams, and formulas), followed by a set of dedicated semantic analyzers that extract structured representations aligned with signal-level semantics. These representations are utilized to drive assertion synthesis via multi-step chain-of-thought (CoT) prompting. The framework incorporates a mutation-based evaluation approach to assess assertion quality via model checking and further refine the generated assertions. Experimental evaluation across three real-world Register-Transfer Level (RTL) designs demonstrates AssertCoder's superior performance, achieving an average increase of 8.4% in functional correctness and 5.8% in mutation detection compared to existing state-of-the-art approaches.","short_abstract":"Assertion-Based Verification (ABV) is critical for ensuring functional correctness in modern hardware systems. However, manually writing high-quality SVAs remains labor-intensive and error-prone. To bridge this gap, we propose AssertCoder, a novel unified framework that automatically generates high-quality SVAs directl...","url_abs":"https://arxiv.org/abs/2507.10338","url_pdf":"https://arxiv.org/pdf/2507.10338v1","authors":"[\"Enyuan Tian\",\"Yiwei Ci\",\"Qiusong Yang\",\"Yufeng Li\",\"Zhichao Lyu\"]","published":"2025-07-14T14:43:14Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AR\",\"cs.LO\"]","methods":"[\"Large Language Model\"]","has_code":false}