SAPO: Self-Adaptive Process Optimization Makes Small Reasoners Stronger
Kaiyuan Chen, Guangmin Zheng, Jin Wang, Xiaobing Zhou, Xuejie Zhang
Abstract
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
BibTeX
@inproceedings{aaai2026_saposelfadaptive,
title = {SAPO: Self-Adaptive Process Optimization Makes Small Reasoners Stronger},
author = {Kaiyuan Chen and Guangmin Zheng and Jin Wang and Xiaobing Zhou and Xuejie Zhang},
booktitle = {AAAI 2026},
year = {2026}
}