An Executable Benchmark for LLM-Based HLS Repair:Design Complexity and Repair Underconstraint.

arXiv:2610.03971v1 Announce Type: cross Abstract: Automated repair of High-Level Synthesis (HLS) designs using large language models (LLMs) is an emerging but underexplored problem. While LLM-based repair shows strong results on register-transfer level (RTL) V