mlsanityData to 14 Oct 2026

SVAgent: AI Agent for Hardware Security Verification Assertion

arXiv 2507.16203 ↗First posted 22 Jul 2025cs.CR cs.AI cs.ARcited by 1

Not on the map. Why?

Abstract (arXiv)

Verification using SystemVerilog assertions (SVA) is one of the most popular methods for detecting circuit design vulnerabilities. However, with the globalization of integrated circuit design and the continuous upgrading of security requirements, the SVA development model has exposed major limitations. It is not only inefficient in development, but also unable to effectively deal with the increasing number of security vulnerabilities in modern complex integrated circuits. In response to these challenges, this paper proposes an innovative SVA automatic generation framework SVAgent. SVAgent introduces a requirement decomposition mechanism to transform the original complex requirements into a structured, gradually solvable fine-grained problem-solving chain. Experiments have shown that SVAgent can effectively suppress the influence of hallucinations and random answers, and the key evaluation indicators such as the accuracy and consistency of the SVA are significantly better than existing frameworks. More importantly, we successfully integrated SVAgent into the most mainstream integrated circuit vulnerability assessment framework and verified its practicality and reliability in a real engineering design environment.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 19 of its 49 references that are in the map. First posted on arXiv 22 Jul 2025.

Builds on

19 of 49 references.

References · 19

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  2. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  3. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 619
  4. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  5. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 488
  6. 2021Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributionscited by 431
  7. 2022Emergent Analogical Reasoning in Large Language Modelscited by 240
  8. 2023MathPrompter: Mathematical Reasoning using Large Language Modelscited by 236
  9. 2023VeriGen: A Large Language Model for Verilog Code Generationcited by 200
  10. 2023Full Parameter Fine-tuning for Large Language Models with Limited Resourcescited by 134
  11. 2024Data-efficient Fine-tuning for LLM-based Recommendationcited by 104
  12. 2024Bugs in Large Language Models Generated Code: An Empirical Studycited by 60
7 more
  1. 2024Understanding the Performance and Estimating the Cost of LLM Fine-Tuningcited by 48
  2. 2021In-IDE Code Generation from Natural Language: Promise and Challengescited by 42
  3. 2023GPT-4 Can't Reasoncited by 40
  4. 2024Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layerscited by 25
  5. 2024ChIRAAG: ChatGPT Informed Rapid and Automated Assertion Generationcited by 16
  6. 2023DIVAS: An LLM-based End-to-End Framework for SoC Security Analysis and Policy-based Protectioncited by 12
  7. 2021A Survey of Microarchitectural Side-channel Vulnerabilities, Attacks and Defenses in Cryptographycited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026A Survey on LLM-Integrated Hardware Design Verificationcited by 0