Pith. sign in

REVIEW 3 cited by

VFlow: Discovering Optimal Agentic Workflows for Verilog Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.03723 v2 pith:VPJB7OTO submitted 2025-03-30 cs.AR cs.MA

Yangbo Wei , Zhen Huang , Huang Li , Wei W. Xing , Ting-Jung Lin , Lei He This is my paper · ORCID
classification cs.ARcs.MA
keywords vflowhardwareverilogagenticareaautomatedcodecorrectness
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Hardware design automation faces challenges in generating high-quality Verilog code efficiently. This paper introduces VFlow, an automated framework that optimizes agentic workflows for Verilog code generation. Unlike traditional approaches relying on fixed prompts or manually designed flows, VFlow treats workflow discovery as a search over graph-structured LLM invocation sequences. It introduces a multi-population cooperative evolution (CEPE-MCTS) algorithm that balances multiple hardware objectives -- functional correctness, area, power, timing and token cost -- while sharing successful patterns and avoiding repeated failures. Integrated multi-level verification ensures syntactic correctness, functional behavior, and synthesizability. Experiments on VerilogEval and RTLLM2.0 show VFlow improves pass@1 by 20--30\% over prompting baselines and closely matches designer-level area/power. Remarkably, VFlow enables small LLMs to outperform larger models with up to 10.9$\times$ ROI, offering a cost-effective solution for RTL design. This work paves the way for intelligent, automated hardware development, advancing LLM applications in EDA.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ProtocolLLM: RTL Benchmark for SystemVerilog Generation of Communication Protocols

    cs.AR 2025-06 conditional novelty 6.0 of 10

    A new benchmark, ProtocolLLM, evaluates LLM-generated SystemVerilog for SPI, I2C, UART, and AXI and finds most models fail timing-accurate functional checks.

  2. VeriOpt: PPA-Aware High-Quality Verilog Generation via Multi-Role LLMs

    cs.SE 2025-07 conditional novelty 5.0 of 10

    A multi-role LLM prompting framework with PPA-aware in-context learning reports 25/29 functional correctness on RTLLM and up to 88% power, 76% area, and 73% timing gains over its own baseline.

  3. Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects

    cs.AI 2025-07 conditional novelty 3.0 of 10

    A survey that categorizes Graph-augmented LLM Agent research into planning, memory, tool management, and multi-agent design, and outlines open directions.

Pith tools