2026-09-03
1 items 57 entities 66 connections
Processed 57 entities and 66 relations.
RTL verification stimuli generation test plan generation two-stage test plan generation framework testbench generation constrained random generation supervised fine-tuning Group Relative Policy Optimization GRPO with State Mutation tree-based branching mutation strategy mutation testing reinforcement learning for language models reward modeling random test generation functional equivalence checking retrieval-augmented generation iterative refinement multi-agent framework coverage-driven verification RTL design verification golden RTL pass rate mutation detection rate input stimuli sub-unit RTL verification reward sparsity advantage computation sequential circuit verification combinational circuit verification data contamination DeepSeek-R1 Claude-4.0-Sonnet DeepSeek-R1-distill-Qwen-7B LLaMA-3.1-405B Claude3.7-Sonnet ScaleRTL-32B DAPO GRPO with State Mutations: Improving LLM-Based Hardware Test Plan Generation ScaleRTL: scaling LLMs with reasoning data and test-time compute for accurate RTL code generation VerilogEval: evaluating large language models for Verilog code generation BugGen: a self-correcting multi-agent LLM pipeline for realistic RTL bug synthesis VeriDebug Comprehensive Verilog Design Problems (CVDP) benchmark DeepSeekMath: pushing the limits of mathematical reasoning in open language models VeriContaminated: assessing LLM-driven Verilog coding for data contamination RTLLM: an open-source benchmark for design RTL generation with large language model DAPO: an open-source LLM reinforcement learning system at scale Decomposed prompting: a modular approach for solving complex tasks Dimple Vijay Kochar Nathaniel Pinckney Haoxing Ren Brucek Khailany Chenhui Deng MIT NVIDIA Research ScaleRTL dataset SFT training dataset GRPO-SMu training dataset testbench template