R3A: Reliable RTL Repair Framework with Multi-Agent Fault Localization and Stochastic Tree-of-Thoughts Patch Generation

TL;DR

R3A introduces a reliable RTL repair framework leveraging multi-agent fault localization and stochastic Tree-of-Thoughts to enhance bug fixing accuracy and reliability using large language models.

Contribution

The paper presents R3A, a novel LLM-based RTL repair framework with stochastic patch generation and multi-agent fault localization, improving reliability and bug coverage over existing methods.

Findings

Fixes 90.6% of bugs in dataset

Covers 45% more bugs than traditional methods

Achieves 86.7% pass@5 rate on average

Abstract

Repairing RTL bugs is crucial for hardware design and verification. Traditional automatic program repair (APR) methods define dedicated search spaces to locate and fix bugs with program synthesis. However, they heavily rely on fixed templates and can only deal with limited bugs. As an alternative, Large Language Models with the ability to understand code semantics can be explored for RTL repair. However, they suffer from unreliable outcomes due to inherent randomness and long input contexts of RTL code and waveform. To address these challenges, we propose R3A, an LLM-based automatic RTL program repair framework upon the basic model to improve reliability. R3A proposes the stochastic Tree-Of-Thoughts method to control a patch generation agent to explore a validated solution for the bug. The algorithm samples search states according to a heuristic function to balance between exploration and exploitation for a reliable outcome. Besides, R3A proposes a multi-agent fault localization method to find fault candidates as the starting points for the patch generation agent, further increasing the reliability. Experiments show R3A can fix 90.6% of bugs in the RTL-repair dataset within a given time limit, which covers 45% more bugs than traditional methods and other LLM-based approaches, while achieving an 86.7% pass@5 rate on average, showing a high reliability.