跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2608.10090 · v2

CHORUS: Coverage-Guided Agentic RL and Policy Consolidation for Testbench Stimulus Generation

首次提交 2026-08-11 02:02
版本更新 2026-11-19 15:12
雷达观测 2026-11-20 19:58
arXiv ↗PDF ↗

摘要

Testbenches written by large language models can compile and run while leaving entire datapaths idle. We present CHORUS, the first framework to combine coverage-guided agentic reinforcement learning (RL) with policy consolidation for testbench stimulus generation. We train LLM4Cov's final supervised checkpoint to draft testbenches and repair its lowest-scoring draft using simulator feedback, raising CVDP-ECov agentic Pass@1 from 69.2% to 85.5%. Applying the same training to three checkpoints yields similar overall pass rates, yet the policies succeed on different designs. Averaging their weights combines these strengths in a single dense 4B model that reaches 86.7% agentic Pass@1. When simulator rewards select the teacher for each training prompt, the distilled 4B model reaches 88.0%, 13.5 percentage points above DeepSeek-R1 (671B).

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-19 15:12 · 最新观测版本

CHORUS: Coverage-Guided Agentic RL and Policy Consolidation for Testbench Stimulus Generation

Testbenches written by large language models can compile and run while leaving entire datapaths idle. We present CHORUS, the first framework to combine coverage-guided agentic reinforcement learning (RL) with policy consolidation for testbench stimulus generation. We train LLM4Cov's final supervised checkpoint to draft testbenches and repair its lowest-scoring draft using simulator feedback, raising CVDP-ECov agentic Pass@1 from 69.2% to 85.5%. Applying the same training to three checkpoints yields similar overall pass rates, yet the policies succeed on different designs. Averaging their weights combines these strengths in a single dense 4B model that reaches 86.7% agentic Pass@1. When simulator rewards select the teacher for each training prompt, the distilled 4B model reaches 88.0%, 13.5 percentage points above DeepSeek-R1 (671B).

查看此版本解读 →查看此版本原文 ↗