arXiv cs.AI· Venkata Krishna Kumar Vedantam·· 2 天前AI 评分22
硬件设计中 LLM 驱动功能覆盖率收敛的独立数据完整性验证
Independent Data-Integrity Verification for LLM-Driven Functional Coverage Closure in Hardware Design
AI 导读
一个设计无关的覆盖率收敛智能体在异步 FIFO、UART 发送器和 AHB2APB 桥三种 RTL 设计上，将覆盖率从 91.7%、88.9% 和 67.4% 提升至 100%，每次运行均在 8 次迭代预算内完成。
正文 · 原文
Abstract:LLM agents can write directed tests that close functional coverage, but coverage only shows that a state was reached, not that the data on the way there was correct. This is a long-known point in verification and we do not claim it as new. We describe a small coverage-closure agent that applies it to an LLM loop: coverage is read from the report that the simulation itself exports (cocotb-coverage YAML) and never taken from the model's account, and data integrity is checked by scoreboards that are separate from the model. On three architecturally distinct RTL designs (an asynchronous FIFO, a UART transmitter and an AHB2APB bridge) the agent raised coverage from 91.7%, 88.9% and 67.4% to 100% within its 8-iteration budget in every logged run, using one design-agnostic agent. A reactive scoreboard monitor attached to the FIFO's base testbench also found a clock-domain-crossing bug in the author's own stimulus code. The monitor is not yet attached to the LLM-generated tests, so their data integrity is not independently checked; one manual check on a single FIFO test is reported as preliminary. We list the weaknesses of this evidence: three designs, no baseline, no ablation, and logged runs that come from several agent checkpoints.
| Subjects: | Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI); Software Engineering (cs.SE) |
| Cite as: | arXiv:2610.21570 [cs.AR] |
| (or arXiv:2610.21570v1 [cs.AR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21570 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Venkata Krishna Kumar Vedantam [view email]
[v1]
Thu, 15 Oct 2026 09:24:01 UTC (43 KB)
来源：arXiv cs.AI · arxiv.org