SANGAM: SystemVerilog Assertion Generation via Monte Carlo Tree Self-Refine

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gupta, Adarsh, Mali, Bhabesh, Karfa, Chandan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913896491646976
author Gupta, Adarsh
Mali, Bhabesh
Karfa, Chandan
author_facet Gupta, Adarsh
Mali, Bhabesh
Karfa, Chandan
contents Recent advancements in the field of reasoning using Large Language Models (LLMs) have created new possibilities for more complex and automatic Hardware Assertion Generation techniques. This paper introduces SANGAM, a SystemVerilog Assertion Generation framework using LLM-guided Monte Carlo Tree Search for the automatic generation of SVAs from industry-level specifications. The proposed framework utilizes a three-stage approach: Stage 1 consists of multi-modal Specification Processing using Signal Mapper, SPEC Analyzer, and Waveform Analyzer LLM Agents. Stage 2 consists of using the Monte Carlo Tree Self-Refine (MCTSr) algorithm for automatic reasoning about SVAs for each signal, and finally, Stage 3 combines the MCTSr-generated reasoning traces to generate SVA assertions for each signal. The results demonstrated that our framework, SANGAM, can generate a robust set of SVAs, performing better in the evaluation process in comparison to the recent methods.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13983
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SANGAM: SystemVerilog Assertion Generation via Monte Carlo Tree Self-Refine
Gupta, Adarsh
Mali, Bhabesh
Karfa, Chandan
Artificial Intelligence
Recent advancements in the field of reasoning using Large Language Models (LLMs) have created new possibilities for more complex and automatic Hardware Assertion Generation techniques. This paper introduces SANGAM, a SystemVerilog Assertion Generation framework using LLM-guided Monte Carlo Tree Search for the automatic generation of SVAs from industry-level specifications. The proposed framework utilizes a three-stage approach: Stage 1 consists of multi-modal Specification Processing using Signal Mapper, SPEC Analyzer, and Waveform Analyzer LLM Agents. Stage 2 consists of using the Monte Carlo Tree Self-Refine (MCTSr) algorithm for automatic reasoning about SVAs for each signal, and finally, Stage 3 combines the MCTSr-generated reasoning traces to generate SVA assertions for each signal. The results demonstrated that our framework, SANGAM, can generate a robust set of SVAs, performing better in the evaluation process in comparison to the recent methods.
title SANGAM: SystemVerilog Assertion Generation via Monte Carlo Tree Self-Refine
topic Artificial Intelligence
url https://arxiv.org/abs/2506.13983