activity
20242026
most citedComprehensive Verilog Design Problems: A Next-Generation Benchmark Dataset for Evaluating Large Language Models and Agents on RTL Design and Verification

1 citations · 1 across the 4 of their papers we have counts for

collaborators

8 papers

cs.AR2026

GRPO with State Mutations: Improving LLM-Based Hardware Test Plan Generation

Dimple Vijay Kochar, Nathaniel Pinckney, Guan-Ting Liu +4

RTL design often relies heavily on ad-hoc testbench creation early in the design cycle. While large language models (LLMs) show promise for RTL code generation, their ability to re…

cs.LO2025

ReVEAL: GNN-Guided Reverse Engineering for Formal Verification of Optimized Multipliers

Chen Chen, Daniela Kaufmann, Chenhui Deng +3

We present ReVEAL, a graph-learning-based method for reverse engineering of multiplier architectures to improve algebraic circuit verification techniques. Our framework leverages s…

cs.AR2025

ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation

Chenhui Deng, Yun-Da Tsai, Guan-Ting Liu +2

Recent advances in large language models (LLMs) have enabled near-human performance on software coding benchmarks, but their effectiveness in RTL code generation remains limited du…

cs.LG20251 cited

Comprehensive Verilog Design Problems: A Next-Generation Benchmark Dataset for Evaluating Large Language Models and Agents on RTL Design and Verification

Nathaniel Pinckney, Chenhui Deng, Chia-Tung Ho +5

We present the Comprehensive Verilog Design Problems (CVDP) benchmark, a new dataset and infrastructure to advance LLM and agent research in hardware design and verification. CVDP…

cs.LG2025

HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization

Hongzheng Chen, Yingheng Wang, Yaohui Cai +10

While Large Language Models (LLMs) have demonstrated significant advancements in reasoning and agent-based problem-solving, current evaluation methodologies fail to adequately asse…

cs.SE2025

JARVIS: A Multi-Agent Code Assistant for High-Quality EDA Script Generation

Ghasem Pasandi, Kishor Kunal, Varun Tej +8

This paper presents JARVIS, a novel multi-agent framework that leverages Large Language Models (LLMs) and domain expertise to generate high-quality scripts for specialized Electron…