<ul><li>Reasoning is critical for large language models (LLMs) to excel in a wide range of tasks.</li><li>Current LLM reasoning processes are unnecessarily lengthy and incur high token usage costs.</li><li>A token-budget-aware LLM reasoning framework is proposed to dynamically estimate and manage token budgets based on reasoning complexity.</li><li>Experiments show that this method effectively reduces token costs in Chain-of-Thought (CoT) reasoning with minimal performance reduction.</li></ul>

Token-Budget-Aware LLM Reasoning

Discover more