Publications
Research contributions at the intersection of Formal Verification and Generative AI

Conference Papers

2025

LISA: LLM-Informed SystemVerilog Assertion Generation
Subhajit Paul, Ansuman Banerjee, Sumana Ghosh
Accepted at IEEE Computer Society Annual Symposium on VLSI (ISVLSI 2025)
Indian Statistical Institute, Kolkata

Abstract: This paper presents a novel framework that leverages Large Language Models to automatically generate SystemVerilog assertions, supporting reliable RTL development and enhancing verification workflows in Electronic Design Automation.


LLM-Guided Reconciliation for Explainable Robotic Path Planning
Subhajit Paul, Ansuman Banerjee
Accepted at IEEE Autonomic Computing and Self-Organizing Systems (ACSOS 2025)
Indian Statistical Institute, Kolkata

Abstract: This work explores the application of Large Language Models in model reconciliation for robotic path planning, providing explainable solutions for autonomous navigation systems.


2026


SuperSAGA: A Supervisor-Subordinate Agentic workflow for the Generation of Assertions Subhajit Paul, Ansuman Banerjee, Sumana Ghosh
Accepted at 31st Asia and South Pacific Design Automation Conference Special Sessions (ASPDAC 2026)
Indian Statistical Institute, Kolkata

Abstract: SuperSAGA combines Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to guide assertion development based on human-reviewed verification plans using an agentic workflow. The framework translates specifications into syntactically correct assertions, integrates feedback from formal verification tools, and supports iterative refinement using an orchestration of supervisor and subordinate agents.


Research Interests

My research focuses on developing innovative frameworks that bridge Formal Verification and Generative Artificial Intelligence. Key areas include:


Ongoing Research

Currently working on expanding the application of agentic workflows in EDA for automated verification environment generation at the Indian Statistical Institute, Kolkata.


Collaboration & Contact

I’m always interested in collaborating on research projects involving:

Contact: test.dev.paul@gmail.com