Focus Session: LLM4PQC -- An Agentic Framework for Accurate and Efficient Synthesis of PQC Cores

2026-02-10

AI Summary

This work proposes LLM4PQC, a novel framework addressing the challenges in post-quantum cryptography (PQC) hardware design, where translating C reference implementations into high-level synthesis (HLS)-compatible code typically requires extensive manual refactoring and suffers from poor scalability of complex primitives such as NTT accelerators. LLM4PQC introduces, for the first time, a feedback-driven agent architecture that leverages large language models to automatically refactor PQC high-level specifications and C code into synthesizable, HLS-ready C code and generate verification-ready RTL. Functional correctness is ensured through multi-level validation, including C compilation/simulation and RTL simulation. Evaluated on NIST PQC candidates, the framework significantly reduces manual intervention and enhances design space exploration efficiency, successfully producing synthesizable and functionally correct hardware implementations.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Security and Privacy: Applications of cryptography

Abstract

The design of post-quantum cryptography (PQC) hardware is a complex and hierarchical process with many challenges. A primary bottleneck is the conversion of PQC reference codes from C to high-level synthesis (HLS) specifications, which requires extensive manual refactoring [1]-[3]. Another bottleneck is the scalability of synthesis for complex PQC primitives, including number theoretic transform (NTT) accelerators and wide memory interfaces. While large language models (LLMs) have shown remarkable results for coding in general-purpose languages like Python, coding for hardware design is more challenging; feedback-driven and agentic integration are key principles of successful state-of-the-art approaches. Here, we propose LLM4PQC, an LLM-based agentic framework that refactors high-level PQC specifications and reference C codes into HLS-ready and synthesizable C code. Our framework generates and verifies the resulting RTL code. For correctness, we leverage a hierarchy of checks, covering fast C compilation and simulation as well as RTL simulation. Case studies on NIST PQC reference designs demonstrate a reduction in manual effort and accelerated design-space exploration compared to traditional flows. Overall, LLM4PQC provides a powerful and efficient pathway for synthesizing complex hardware accelerators.

Problem

• post-quantum cryptography
• hardware synthesis
• high-level synthesis
• code refactoring
• scalability

Innovation

• LLM4PQC
• post-quantum cryptography
• high-level synthesis
• agentic framework
• hardware acceleration