The paper introduces CARE, a contrastive accuracy reward estimation method that adaptively adjusts reasoning length for large language models. By comparing beneficial length adjustments from online sampled responses, CARE applies adaptive length rewards within Group Relative Policy Optimization without extra hyperparameters or inference cost. Experiments on multiple reasoning benchmarks show that CARE improves Pass@1 by up to 4% while reducing reasoning length by 37%, achieving higher token efficiency.
By Zhengdong He, Yunfan Zhou, Jianguo Yao, Haibing Guan, Xijun Li
The paper introduces Budget‑Efficient Thinking (BET), a two‑stage framework that treats adaptive reasoning as a computational investment, aligning solve‑or‑fold decisions with expected return rather than perceived difficulty. BET learns three distinct behaviors: concise short solves for easy queries, early abstention (nice fold) when further reasoning is unlikely to pay off, and allocating sufficient compute (hero call) for hard‑but‑solvable questions. Experiments on seven benchmarks with three base models show BET cuts reasoning tokens by 54% while boosting accuracy by up to 3.2%, and it transfers effectively to scientific QA and logical reasoning tasks.
By Zhaomeng Zhou, Lan Zhang, Junyang Wang, Mu Yuan, Songlin Liu, Tingzhao Li, Yiqing Hu, Yumeng Zhao
When2Think introduces a post‑training framework that dynamically allocates reasoning depth in Large Reasoning Models based on instance difficulty. The method uses Instance‑level Difficulty‑Aware Control (IDAC) to shape rewards with pre‑computed accuracy and token usage statistics, enabling stable, critic‑free optimization without learned reward models. Experiments on mathematical benchmarks show that When2Think improves accuracy‑efficiency trade‑offs, achieving higher Pass@3 scores while reducing token usage compared to baseline models.
By Jaejun Shim, HyunJin Kim, Young Jin Kim, JinYeong Bak
arXiv:2510.01581v2 Announce Type: replace-cross
Abstract: Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in l...
By Joykirat Singh, Justin Chih-Yao Chen, Archiki Prasad, Elias Stengel-Eskin, Akshay Nambi, Mohit Bansal
arXiv:2606. 07950v1 Announce Type: new Abstract: RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often treats easy, hard, and learnable questions alike through uniform sampling and weighting, leading to inefficient compute allocation.
By Zhanke Zhou, Xiangyu Lu, Chentao Cao, Brando Miranda, Tongliang Liu, Bo Han, Sanmi Koyejo
The paper introduces PORA, a method that teaches large language model agents to decide when to allocate more reasoning steps versus fewer, based on the expected downstream benefit. PORA trains by running each state twice—once with short reasoning and once with long reasoning—and learns to predict the value of extended reasoning. During inference, a controller uses this prediction and remaining budget information to choose the appropriate reasoning length without running both options, improving performance across diverse tasks.
By Bo Yan, Qi Zhang, Zhen Tan, Tianlong Chen, Song Wang