Test-Time Scaling via Error Localization
Merged summary
TL;DR - TTEL is an inference-time scaling algorithm that localizes token-level reasoning errors, truncates at the faulty step, and reuses valid prefixes. It improves reasoning performance while substantially reducing generated-token costs.
- Compares token probabilities under feedback with a null-context baseline to identify where errors begin.
- Branches new generations from the localized error point instead of discarding entire reasoning trajectories.
- Achieves 71.0% pass@64 on LiveCodeBench with Qwen3-8B using roughly half the tokens of independent sampling.
- Outperforms competing test-time baselines on AIME-2025 and HMMT-2025 across two Qwen3 model variants.
Sources (1)
Test-Time Scaling via Error Localization
TL;DR - TTEL is an inference-time scaling algorithm that localizes token-level reasoning errors, truncates at the faulty step, and reuses valid prefixes. It improves reasoning performance while substantially reducing generated-token costs.
- Compares token probabilities under feedback with a null-context baseline to identify where errors begin.
- Branches new generations from the localized error point instead of discarding entire reasoning trajectories.
- Achieves 71.0% pass@64 on LiveCodeBench with Qwen3-8B using roughly half the tokens of independent sampling.
- Outperforms competing test-time baselines on AIME-2025 and HMMT-2025 across two Qwen3 model variants.