When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning

Xiaoyun Zhang, Jingqing Ruan, Xing Ma, Yawen Zhu, Haodong Zhao, Hao Li, Jiansong Chen, Ke Zeng, Xunliang Cai


Abstract
Large reasoning models (LRMs) achieve remarkable performance via long reasoning chains, but often incur excessive computational overhead due to redundant reasoning, especially on simple tasks. In this work, we systematically quantify the upper bounds of LRMs under both Long-Thinking and No-Thinking modes, and uncover the phenomenon of “Internal Self-Recovery Mechanism” where models implicitly supplement reasoning during answer generation. Building on this insight, we propose Adaptive Self-Recovery Reasoning (ASRR), a framework that suppresses unnecessary reasoning and enables implicit recovery. By introducing accuracy-aware length reward regulation, ASRR adaptively allocates reasoning effort according to problem difficulty, achieving high efficiency with negligible performance sacrifice. Experiments across multiple benchmarks and models show that, compared with GRPO, ASRR reduces reasoning budget by up to 32.5% (1.5B) and 25.7% (7B) with minimal accuracy loss (1.2% and 0.6% pass@1), and significantly boosts harmless rates on safety benchmarks (up to +21.7%). Our results highlight the potential of ASRR for enabling efficient, adaptive, and safer reasoning in LRMs.
Anthology ID:
2025.findings-emnlp.310
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5808–5828
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.310/
DOI:
Bibkey:
Cite (ACL):
Xiaoyun Zhang, Jingqing Ruan, Xing Ma, Yawen Zhu, Haodong Zhao, Hao Li, Jiansong Chen, Ke Zeng, and Xunliang Cai. 2025. When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 5808–5828, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning (Zhang et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.310.pdf
Checklist:
 2025.findings-emnlp.310.checklist.pdf