ROSUM-MCTS: Monte Carlo Tree Search-Inspired HDL Code Summarization with Structural Rewards

2026-06-05

AI Summary

This work addresses the limited performance and poor robustness of large language models in generating summaries for hardware description languages (HDLs), such as VHDL and Verilog. To overcome these challenges, the authors propose a structured summarization approach inspired by Monte Carlo tree search, featuring a hierarchical candidate expansion mechanism. The method employs a composite reward function that integrates functional correctness, local content adequacy, and linguistic fluency, optimizing the generation process through reinforcement learning. Experimental results demonstrate that the proposed approach significantly outperforms existing baselines on the VHDL-eval and Verilog-eval benchmarks and exhibits strong robustness against superficial perturbations, such as variable renaming.

Abstract

Large language models (LLMs) have shown promise in code summarization, yet their effectiveness for Hardware Description Languages (HDLs) like VHDL and Verilog remains underexplored. We propose ROSUM-MCTS, an LLM-guided approach inspired by Monte Carlo Tree Search (MCTS) that refines summaries through structured exploration and reinforcement-driven optimization. Our method integrates both local and global context via a hierarchical candidate expansion mechanism and optimizes summaries using a composite reward function balancing functional correctness (FC), local content adequacy (LCA), and fluency. We evaluate ROSUM-MCTS on the VHDL-eval and Verilog-eval datasets, demonstrating its consistent outperformance over baseline methods by leveraging structured bottom-up refinement and reinforcement-based optimization. Ablation studies confirm the necessity of both local and global expansion strategies, as well as the importance of balancing FC and LCA for optimal performance. Furthermore, ROSUM-MCTS proves robust against superficial modifications, such as variable renaming, maintaining summary quality where baselines degrade. These results establish ROSUM-MCTS as an effective and robust HDL summarization framework, paving the way for further research into reinforcement-enhanced code summarization.

Problem

• HDL code summarization
• large language models
• functional correctness
• content adequacy
• code summarization robustness

Innovation

• Monte Carlo Tree Search
• HDL code summarization
• reinforcement-based optimization
• structured candidate expansion
• composite reward function