SelfBudgeter Introduces Adaptive Token Budgets for LLM Reasoning

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. getnews.me/selfbudgeter-introduces-... #selfbudgeter #llm #tokenbudget