跳到正文
arXiv cs.AI· Minh Luu, Michael Quinn, Aakash Tyagi, David Houngninou, Jiang Hu·· 23 小时前AI 评分24

BugGen 2.0:重新划分 LLM 在可扩展 RTL Bug 合成中的角色

BugGen 2.0: Rethinking the Roles of LLMs for Scalable RTL Bug Synthesis

AI 导读

BugGen 2.0 将 RTL Bug 合成中的结构分析、目标选择与验证交给确定性算法,LLM 只负责局部语义改写,在四个 OpenTitan IP 模块和 FabScalar 上配合三个 LLM 均达到全部可编译 Bug 场景配额,16 种变异类型中覆盖 14-16 种。

正文 · 原文

View PDF HTML (experimental)

Abstract:AI-assisted RTL localization and debugging need ground-truth bug datasets with known locations and observable failures, while testbench grading uses injected bugs to measure detection capability. Creating such datasets at scale remains a major EDA challenge. BugGen 1.0 shows that Large Language Models (LLMs) can generate context-aware RTL mutations. Still, it relies on the model for both choosing where to mutate and generating the edit, which increases inference costs and can lead to invalid choices. BugGen 2.0 changes this division of labor. Deterministic algorithms handle structural analysis, target selection, and validation, while the LLM focuses on localized semantic rewriting. Across four OpenTitan IP blocks and FabScalar with three LLMs, BugGen 2.0 reaches every requested quota of compilable bug scenarios that cause at least two test failures, with 14-16 of 16 configured mutation types represented. In completed same-model comparisons, it reduces token use by 6.8x-15.4x relative to BugGen 1.0 and 1.5x-7.9x relative to Firefly. BugGen 2.0 also expands the dataset without simulating every new bug. After finding accepted scenarios with observable failures, it generates alternative mutations at the same locations, simulates only a subset, and estimates acceptance for the rest. This skips 63.6% of AES and 33.9% of FabScalar variant simulations. Full simulation finds that 77.7% of AES variants and 95.2% of FabScalar variants are accepted, with a 1.09% estimation error on the directly comparable FabScalar set. These results show that focusing LLMs on semantic rewriting lowers inference and simulation cost while improving consistency across models and designs.
Comments: 7 pages, 2 figures, 7 tables
Subjects: Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.23091 [cs.SE]
  (or arXiv:2611.23091v1 [cs.SE] for this version)
  https://doi.org/10.48550/arXiv.2611.23091

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Minh Luu [view email]
[v1] Tue, 17 Nov 2026 17:11:54 UTC (247 KB)

来源:arXiv cs.AI · arxiv.org