Metraipolis › archive › dc_707c4eb213c8
StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning — arXiv:2611.08403
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08403
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:42:00.965Z
- SHA-256 of the archived text
245f20b554171b68cea0c7474c0d21f7c4dc1574e4d29f13910518265c1dd7f4- Stable URL of this page
https://metraipolis.com/documento/dc_707c4eb213c8
How to cite
StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning — arXiv:2611.08403 — arXiv (en), https://arxiv.org/abs/2611.08403 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_707c4eb213c8 (Metraipolis archive dc_707c4eb213c8, sha256 245f20b554171b68cea0c7474c0d21f7c4dc1574e4d29f13910518265c1dd7f4)
BibTeX
@misc{dc707c4eb213c8,
title = {StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning — arXiv:2611.08403},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08403},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_707c4eb213c8; sha256 245f20b554171b68cea0c7474c0d21f7c4dc1574e4d29f13910518265c1dd7f4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08403. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.08403 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-06T14:18:42.658Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).