CLJan 28

SAPO: Self-Adaptive Process Optimization Makes Small Reasoners Stronger

arXiv:2601.20312v11 citationsh-index: 23
Originality Incremental advance
AI Analysis

This work improves self-evolution methods for small language models, with domain-specific applications in mathematics and coding.

The paper tackles the problem of self-improvement in Small Language Models by addressing the reasoner-verifier gap and computational inefficiency of Monte Carlo process supervision, proposing SAPO which outperforms existing methods on mathematics and code tasks.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes