An Agentic Python Framework for LLM-Driven UVM Testbench Synthesis with Closed-Loop Compiler Feedback

Protocol bridge verification is a persistent bottleneck in SoC development: for every new bridge instance, engineers hand-craft a full UVM testbench from scratch, consuming 40--100 engineering hours of bring-up effort. We present an agentic Python framework that generates complete, protocol-aware UVM testbenches for arbitrary IP and subsystem configurations from a structured Verification Manifest---a JSON specification encoding interface topology, protocol semantics, and coverage intent. The framework employs a dual closed-loop architecture: an inner compiler feedback loop that injects categorised UVM diagnostics rather than raw tool output, and an outer coverage loop driven by intent-gap analysis against the Manifest. Validated on the AMBA AHB-to-APB bridge---a representative production protocol bridge with a 7-state control FSM, two-phase APB handshake, and non-trivial burst serialisation logic---the framework achieves 96.8% functional coverage, a $4.7\times$ bring-up speedup, and a Protocol Verification Completeness score of 0.87, with only 2.1% of the generated 4,623-line testbench requiring human correction. The generated scoreboard independently identified a critical RTL functional fault that the manual baseline missed entirely. Generalisation across four protocol families confirms that speedup increases with protocol complexity, ranging from $3.1\times$ (APB Subordinate) to $6.1\times$ (CHI Subordinate).

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-12
DOI
https://doi.org/10.48550/arxiv.2611.16202
Primary Topic
Embedded Systems Design Techniques
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

An Agentic Python Framework for LLM-Driven UVM Testbench Synthesis with Closed-Loop Compiler Feedback

Vikash Kumar
arXiv (Cornell University)
Embedded Systems Design Techniques
preprint

An Agentic Python Framework for LLM-Driven UVM Testbench Synthesis with Closed-Loop Compiler Feedback

Vikash Kumar
preprint en

Abstract

Protocol bridge verification is a persistent bottleneck in SoC development: for every new bridge instance, engineers hand-craft a full UVM testbench from scratch, consuming 40--100 engineering hours of bring-up effort. We present an agentic Python framework that generates complete, protocol-aware UVM testbenches for arbitrary IP and subsystem configurations from a structured Verification Manifest---a JSON specification encoding interface topology, protocol semantics, and coverage intent. The framework employs a dual closed-loop architecture: an inner compiler feedback loop that injects categorised UVM diagnostics rather than raw tool output, and an outer coverage loop driven by intent-gap analysis against the Manifest. Validated on the AMBA AHB-to-APB bridge---a representative production protocol bridge with a 7-state control FSM, two-phase APB handshake, and non-trivial burst serialisation logic---the framework achieves 96.8% functional coverage, a $4.7\times$ bring-up speedup, and a Protocol Verification Completeness score of 0.87, with only 2.1% of the generated 4,623-line testbench requiring human correction. The generated scoreboard independently identified a critical RTL functional fault that the manual baseline missed entirely. Generalisation across four protocol families confirms that speedup increases with protocol complexity, ranging from $3.1\times$ (APB Subordinate) to $6.1\times$ (CHI Subordinate).

arXiv (Cornell University)
Embedded Systems Design Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon