Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Kaiyuan, Zheng, Guangmin, Wang, Jin, Zhou, Xiaobing, Zhang, Xuejie
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.20312
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914300290924544
author Chen, Kaiyuan
Zheng, Guangmin
Wang, Jin
Zhou, Xiaobing
Zhang, Xuejie
author_facet Chen, Kaiyuan
Zheng, Guangmin
Wang, Jin
Zhou, Xiaobing
Zhang, Xuejie
contents Existing self-evolution methods overlook the influence of fine-grained reasoning steps, which leads to the reasoner-verifier gap. The computational inefficiency of Monte Carlo (MC) process supervision further exacerbates the difficulty in mitigating the gap. Motivated by the Error-Related Negativity (ERN), which the reasoner can localize error following incorrect decisions, guiding rapid adjustments, we propose a Self-Adaptive Process Optimization (SAPO) method for self-improvement in Small Language Models (SLMs). SAPO adaptively and efficiently introduces process supervision signals by actively minimizing the reasoner-verifier gap rather than relying on inefficient MC estimations. Extensive experiments demonstrate that the proposed method outperforms most existing self-evolution methods on two challenging task types: mathematics and code. Additionally, to further investigate SAPO's impact on verifier performance, this work introduces two new benchmarks for process reward models in both mathematical and coding tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20312
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SAPO: Self-Adaptive Process Optimization Makes Small Reasoners Stronger
Chen, Kaiyuan
Zheng, Guangmin
Wang, Jin
Zhou, Xiaobing
Zhang, Xuejie
Computation and Language
Existing self-evolution methods overlook the influence of fine-grained reasoning steps, which leads to the reasoner-verifier gap. The computational inefficiency of Monte Carlo (MC) process supervision further exacerbates the difficulty in mitigating the gap. Motivated by the Error-Related Negativity (ERN), which the reasoner can localize error following incorrect decisions, guiding rapid adjustments, we propose a Self-Adaptive Process Optimization (SAPO) method for self-improvement in Small Language Models (SLMs). SAPO adaptively and efficiently introduces process supervision signals by actively minimizing the reasoner-verifier gap rather than relying on inefficient MC estimations. Extensive experiments demonstrate that the proposed method outperforms most existing self-evolution methods on two challenging task types: mathematics and code. Additionally, to further investigate SAPO's impact on verifier performance, this work introduces two new benchmarks for process reward models in both mathematical and coding tasks.
title SAPO: Self-Adaptive Process Optimization Makes Small Reasoners Stronger
topic Computation and Language
url https://arxiv.org/abs/2601.20312