Verifier‑guided backtracking sampler lets 0.5B models code like 2‑4B rivals
On the LiveCodeBench coding benchmark, the 0.5B model with VGB achieves Pass@1 comparable to 2‑4B models, without any weight changes. The method uses a probabilistic backtracking random walk guided by a process verifier, offering provable robustness to verifier errors and scaling potential for larger models.