BugGen: A Self-Correcting Multi-Agent LLM Pipeline for Realistic RTL Bug Synthesis

TL;DR

BugGen is an autonomous multi-agent pipeline that uses LLMs to generate, insert, and validate realistic RTL bugs, significantly improving dataset diversity, bug detection, and verification efficiency for hardware design validation.

Contribution

It introduces BugGen, the first fully autonomous multi-agent system leveraging LLMs for systematic RTL bug generation, validation, and dataset creation.

Findings

Generated 500 unique bugs with 94% functional accuracy.

Achieved a throughput of 17.7 bugs per hour, over five times faster than manual methods.

Improved ML failure triage accuracy using BugGen-generated datasets.

Abstract

Hardware complexity continues to strain verification resources, motivating the adoption of machine learning (ML) methods to improve debug efficiency. However, ML-assisted debugging critically depends on diverse and scalable bug datasets, which existing manual or automated bug insertion methods fail to reliably produce. We introduce BugGen, a first of its kind, fully autonomous, multi-agent pipeline leveraging Large Language Models (LLMs) to systematically generate, insert, and validate realistic functional bugs in RTL. BugGen partitions modules, selects mutation targets via a closed-loop agentic architecture, and employs iterative refinement and rollback mechanisms to ensure syntactic correctness and functional detectability. Evaluated across five OpenTitan IP blocks, BugGen produced 500 unique bugs with 94% functional accuracy and achieved a throughput of 17.7 validated bugs per hour-over five times faster than typical manual expert insertion. Additionally, BugGen identified 104 previously undetected bugs in OpenTitan regressions, highlighting its utility in exposing verification coverage gaps. Compared against Certitude, BugGen demonstrated over twice the syntactic accuracy, deeper exposure of testbench blind spots, and more functionally meaningful and complex bug scenarios. Furthermore, when these BugGen-generated datasets were employed to train ML-based failure triage models, we achieved high classification accuracy (88.1%-93.2%) across different IP blocks, confirming the practical utility and realism of generated bugs. BugGen thus provides a scalable solution for generating high-quality bug datasets, significantly enhancing verification efficiency and ML-assisted debugging.