StepBack：步级错误定位重采样降低推理成本
StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning
给采样太多条思维链太烧钱的场景：这篇 arXiv 论文只定位并重写出错的那一步，token 省四成还不掉准确率。
StepBack 是一种测试时推理的重采样方法，先用轻量信号在少量草稿轨迹中定位首个可能出错的步骤，再重采样该步及其后续内容，最后做多数投票。在 7 个数学推理和多跳问答基准上，StepBack 的平均准确率与自一致性（SC）解码持平，同时最多减少 41.26% 的 token 用量。它还能与 Adaptive Consistency 等自适应推理方法组合，进一步压缩推理开销。
StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning
Self-consistency (SC) is a widely used decoding strategy for improving chain-of-thought reasoning, but it requires sampling many complete reasoning trajectories with a preset budget. Its efficient variants reduce the cost mainly by stopping full-trajectory sampling early or distributing the number of samples across questions. In this paper, we propose StepBack, a step-level error-localized resampling method for efficient test-time reasoning. Given a small set of draft trajectories, StepBack localizes likely first error positions using lightweight signals and then resamples the detected error step and its suffix, followed by majority answer voting. Empirically, StepBack matches the accuracy of SC on average across seven mathematical reasoning and multi-hop QA benchmarks, while reducing token usage by up to 41.26%. In addition, by nature, StepBack can be combined with adaptive inference methods such as Adaptive Consistency, further improving their inference-time efficiency.