Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

AdaptThink: Reasoning Models Can Learn When to Think

About

Recently, large reasoning models have achieved impressive performance on various tasks by employing human-like deep thinking. However, the lengthy thinking process substantially increases inference overhead, making efficiency a critical bottleneck. In this work, we first demonstrate that NoThinking, which prompts the reasoning model to skip thinking and directly generate the final solution, is a better choice for relatively simple tasks in terms of both performance and efficiency. Motivated by this, we propose AdaptThink, a novel RL algorithm to teach reasoning models to choose the optimal thinking mode adaptively based on problem difficulty. Specifically, AdaptThink features two core components: (1) a constrained optimization objective that encourages the model to choose NoThinking while maintaining the overall performance; (2) an importance sampling strategy that balances Thinking and NoThinking samples during on-policy training, thereby enabling cold start and allowing the model to explore and exploit both thinking modes throughout the training process. Our experiments indicate that AdaptThink significantly reduces the inference costs while further enhancing performance. Notably, on three math datasets, AdaptThink reduces the average response length of DeepSeek-R1-Distill-Qwen-1.5B by 53% and improves its accuracy by 2.4%, highlighting the promise of adaptive thinking-mode selection for optimizing the balance between reasoning quality and efficiency. Our codes and models are available at https://github.com/THU-KEG/AdaptThink.

Jiajie Zhang, Nianyi Lin, Lei Hou, Ling Feng, Juanzi Li• 2025

Related benchmarks

TaskDatasetResultRank
Mathematical ReasoningMATH500 (test)
Accuracy87.8
895
Mathematical ReasoningMATH 500
Accuracy (Acc)90.6
543
Mathematical ReasoningGSM8K
Accuracy90.29
499
Mathematical ReasoningOlympiad Bench
Accuracy59.1
222
Mathematical ReasoningMATH 500
Accuracy91.6
221
Mathematical ReasoningAIME 2024 (test)
Accuracy50.7
209
Mathematical ReasoningAMC23
PASS@1 Accuracy79.1
207
Mathematical ReasoningAMC 2023
Accuracy86.88
144
Math ReasoningGSM8K
Accuracy91
126
Mathematical ReasoningAIME24
Pass@1 Accuracy54.8
117
Showing 10 of 98 rows
...

Other info

Follow for update