CORTEXA
← Browse

Cangyuan Li

2 papers indexed

arxivcs.ARcs.LG2026-07-31

RTLCurator: Label-Efficient Data Curation for RTL Generation

Siyang Cai, Cangyuan Li, Wenjing Chang, Kun Wang, Haoyu Gao, Yinhe Han, et al.

Training large language models (LLMs) to write register-transfer level (RTL) requires large corpora of paired specifications and code, and such data is scarce enough that most public corpora are now synthesized. Synthesis provides scale but not correctness, and in two widely used…

View free PDFSource page
arxivcs.SEcs.AI2026-07-18

CLOSER-Bench: Evaluating Budgeted Cross-Stage Design Closure for Hardware Agents

Peilong Zhou, Zhirong Chen, Cangyuan Li, Haoyu Gao, Kaiyan Chang, Ziming Qu, et al.

Hardware engineering exposes coding agents to a form of long-horizon work that is difficult to capture with pass-at-k: progress is continuous, tool feedback is delayed and heterogeneous, and a backend failure may require revising RTL rather than tuning another physical-design par…

View free PDFSource page