Clover: A Neural-Symbolic Agentic Harness with Stochastic Tree-of-Thoughts for Verified RTL Repair

ArXi:2604.17288v1 Announce Type: cross RTL program repair remains a critical bottleneck in hardware design and verification. Traditional automatic program repair (APR) methods rely on predefined templates and synthesis, limiting their bug coverage. Large language models (LLMs) and coding agents based on them offer flexibility but suffer from randomness and context corruption when handling long RTL code and waveforms. We present Clover, a neural-symbolic agentic harness that orchestrates RTL repair as a structured search over code manipulations to explore a validated solution for the bug.