SelfBudgeter predicts a token budget before reasoning, cutting response length by 61 % for a 1.5 B model and 48 % for a 7 B model on benchmarks like GSM8K, MATH500 and AIME2025. https://getnews.me/selfbudgeter-introduces-adaptive-token-budgets-for-llm-reasoning/ #selfbudgeter #llm #tokenbudget

informed decisions about continuing or interrupting the process. Furthermore, our method enables direct manipulation of reasoning length via pre-filling token budget. Experimental results demonstrate that SelfBudgeter can rationally allocate budgets [4/5 of https://arxiv.org/abs/2505.11274v1]

reasoning cost based on the difficulty of the query. Then, we introduce budget-guided GPRO for reinforcement learning, which effectively maintains accuracy while reducing output length. SelfBudgeter allows users to anticipate generation time and make [3/5 of https://arxiv.org/abs/2505.11274v1]

and prolonged user latency. To address this challenge, we propose SelfBudgeter - a self-adaptive controllable reasoning strategy for efficient reasoning. Our approach adopts a dual-phase training paradigm: first, the model learns to pre-estimate the [2/5 of https://arxiv.org/abs/2505.11274v1]

Zheng Li, Qingxiu Dong, Jingyuan Ma, Di Zhang, Zhifang Sui: SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning https://arxiv.org/abs/2505.11274 https://arxiv.org/pdf/2505.11274 https://arxiv.org/html/2505.11274