mlsanityData to 14 Oct 2026

Agentic AI-based Coverage Closure for Formal Verification

arXiv 2603.03147 ↗First posted 3 Mar 2026cs.AIcited by 0

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Coverage closure is a critical requirement in Integrated Chip (IC) development process and key metric for verification sign-off. However, traditional exhaustive approaches often fail to achieve full coverage within project timelines. This study presents an agentic AI-driven workflow that utilizes Large Language Model (LLM)-enabled Generative AI (GenAI) to automate coverage analysis for formal verification, identify coverage gaps, and generate the required formal properties. The framework accelerates verification efficiency by systematically addressing coverage holes. Benchmarking open-source and internal designs reveals a measurable increase in coverage metrics, with improvements correlated to the complexity of the design. Comparative analysis validates the effectiveness of this approach. These results highlight the potential of agentic AI-based techniques to improve formal verification productivity and support comprehensive coverage closure.

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 8 of its 15 references that are in the map. First posted on arXiv 3 Mar 2026.

Builds on

8 of 15 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025A Survey on Agent Workflow -- Status and Future2 Aug
  2. 2025Hey AI, Generate Me a Hardware Code! Agentic AI-based Hardware Design & Verification3 Jul
  3. 2025Comprehensive Verilog Design Problems: A Next-Generation Benchmark Dataset for Evaluating Large Language Models and Agents on RTL Design and Verification17 Jun

Other references · 5

  1. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Applicationcited by 55
  2. 2024AssertLLM: Generating Hardware Verification Assertions from Design Specifications via Multi-LLMscited by 31
  3. 2024Advancing Agentic Systems: Dynamic Task Decomposition, Tool Integration and Evaluation using Novel Metrics and Datasetcited by 24
  4. 2025Saarthi: The First AI Formal Verification Engineercited by 8
  5. 2025Know the Ropes: A Heuristic Strategy for LLM-based Multi-Agent System Designcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Multi-Agent Generative AI Framework for IC Module-Level Verification Automation
  2. 2026GoGoTB: Agentic RTL Verification with Specification-Grounded Coverage Closure
  3. 2026AgentDV: Closed-Loop Agentic AI for Hardware Design Verification
  4. 2026CovR: Coverage-Aware Hardware Verification via Reasoning-Guided Reinforcement Learning
  5. 2026Automating Formal Verification with Agent-Guided Tree Search
  6. 2026Open-Source LLM-Driven Formal Verification: A Multi-Agent Pipeline for RTL Repair
  7. 2026Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification
  8. 2026UCAgent: An End-to-End Agent for Block-Level Functional Verification