Error Localization Cuts Inference Cost While Boosting Reasoning Accuracy
TTEL spots the exact token where a model errs, truncates the bad continuation, and branches a fresh generation, preserving the correct prefix. On Qwen3‑8B it reaches 71 % pass@64 on LiveCodeBench with half the tokens of independent sampling, and beats other test‑time methods on AIME‑2025 and HMMT‑2025.