Papers
arxiv:2608.10090

CHORUS: Complementary Experts for High-Coverage Testbench Stimulus Generation

Published on Aug 10
Authors:
,
,
,
,
,

Abstract

CHORUS improves hardware verification code generation by merging diverse expert models via staged supervised fine-tuning and reinforcement learning, surpassing much larger models.

Large language models (LLMs) have advanced code generation, where executable feedback provides a more reliable learning signal than textual imitation alone. Hardware verification is an important application of code generation and accounts for a substantial fraction of modern chip design effort, with high-coverage testbench stimulus generation as a key task. We present CHORUS, a post-training framework that pushes performance beyond what a conventional supervised fine-tuning (SFT)-to-reinforcement learning (RL) pipeline achieves. CHORUS builds on two observations. First, staged SFT produces behaviorally diverse checkpoints, and dense-reward RL turns them into strong experts with comparable aggregate performance but distinct task-level strengths. Second, these complementary strengths can be exploited through either training-free model merging or further post-training to outperform the best individual expert. By consolidating the resulting specialists into a single 4B model, CHORUS achieves 88.0% Pass@1 on CVDP-ECov, outperforming DeepSeek-R1 (671B) by 13.5 percentage points.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2608.10090
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2608.10090 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2608.10090 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2608.10090 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.