Veri-Sure: A Contract-Aware Multi-Agent Framework with Temporal Tracing and Formal Verification for Correct RTL Code Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jiale, Zhou, Taiyu, Jiang, Tianqi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908792142168064
author Liu, Jiale
Zhou, Taiyu
Jiang, Tianqi
author_facet Liu, Jiale
Zhou, Taiyu
Jiang, Tianqi
contents In the rapidly evolving field of Electronic Design Automation (EDA), the deployment of Large Language Models (LLMs) for Register-Transfer Level (RTL) design has emerged as a promising direction. However, silicon-grade correctness remains bottlenecked by: (i) limited test coverage and reliability of simulation-centric evaluation, (ii) regressions and repair hallucinations introduced by iterative debugging, and (iii) semantic drift as intent is reinterpreted across agent handoffs. In this work, we propose Veri-Sure, a multi-agent framework that establishes a design contract to align agents' intent and uses a patching mechanism guided by static dependency slicing to perform precise, localized repairs. By integrating a multi-branch verification pipeline that combines trace-driven temporal analysis with formal verification consisting of assertion-based checking and boolean equivalence proofs, Veri-Sure enables functional correctness beyond pure simulations. We also introduce VerilogEval-v2-EXT, extending the original benchmark with 53 more industrial-grade design tasks and stratified difficulty levels, and show that Veri-Sure achieves state-of-the-art verified-correct RTL code generation performance, surpassing standalone LLMs and prior agentic systems.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19747
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Veri-Sure: A Contract-Aware Multi-Agent Framework with Temporal Tracing and Formal Verification for Correct RTL Code Generation
Liu, Jiale
Zhou, Taiyu
Jiang, Tianqi
Hardware Architecture
Artificial Intelligence
Software Engineering
In the rapidly evolving field of Electronic Design Automation (EDA), the deployment of Large Language Models (LLMs) for Register-Transfer Level (RTL) design has emerged as a promising direction. However, silicon-grade correctness remains bottlenecked by: (i) limited test coverage and reliability of simulation-centric evaluation, (ii) regressions and repair hallucinations introduced by iterative debugging, and (iii) semantic drift as intent is reinterpreted across agent handoffs. In this work, we propose Veri-Sure, a multi-agent framework that establishes a design contract to align agents' intent and uses a patching mechanism guided by static dependency slicing to perform precise, localized repairs. By integrating a multi-branch verification pipeline that combines trace-driven temporal analysis with formal verification consisting of assertion-based checking and boolean equivalence proofs, Veri-Sure enables functional correctness beyond pure simulations. We also introduce VerilogEval-v2-EXT, extending the original benchmark with 53 more industrial-grade design tasks and stratified difficulty levels, and show that Veri-Sure achieves state-of-the-art verified-correct RTL code generation performance, surpassing standalone LLMs and prior agentic systems.
title Veri-Sure: A Contract-Aware Multi-Agent Framework with Temporal Tracing and Formal Verification for Correct RTL Code Generation
topic Hardware Architecture
Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2601.19747