Think with Self-Decoupling and Self-Verification: Automated RTL Design with Backtrack-ToT

TL;DR

VeriBToT leverages self-decoupling and self-verification in LLM reasoning to improve automated Verilog generation for IC design, addressing previous challenges in correctness and efficiency.

Contribution

The paper introduces VeriBToT, a novel LLM reasoning paradigm that integrates top-down and verification strategies for automated RTL Verilog generation.

Findings

Enhanced Verilog generation accuracy

Reduced token costs through modular design

Effective self-verification of intermediate steps

Abstract

Large language models (LLMs) hold promise for automating integrated circuit (IC) engineering using register transfer level (RTL) hardware description languages (HDLs) like Verilog. However, challenges remain in ensuring the quality of Verilog generation. Complex designs often fail in a single generation due to the lack of targeted decoupling strategies, and evaluating the correctness of decoupled sub-tasks remains difficult. While the chain-of-thought (CoT) method is commonly used to improve LLM reasoning, it has been largely ineffective in automating IC design workflows, requiring manual intervention. The key issue is controlling CoT reasoning direction and step granularity, which do not align with expert RTL design knowledge. This paper introduces VeriBToT, a specialized LLM reasoning paradigm for automated Verilog generation. By integrating Top-down and design-for-verification (DFV) approaches, VeriBToT achieves self-decoupling and self-verification of intermediate steps, constructing a Backtrack Tree of Thought with formal operators. Compared to traditional CoT paradigms, our approach enhances Verilog generation while optimizing token costs through flexible modularity, hierarchy, and reusability.