Efficient Reasoning Models: A Survey

TMLR Paper4730 Authors

Abstract: Reasoning models have demonstrated remarkable progress in solving complex and logic-intensive tasks by generating extended Chain-of-Thoughts (CoTs) prior to arriving at a final answer. Yet, the emergence of this “slow-thinking” paradigm, with numerous tokens generated in sequence, inevitably introduces substantial computational overhead. To this end, it highlights an urgent need for effective acceleration. This survey aims to provide a comprehensive overview of recent advances in efficient reasoning. It categorizes existing works into three key directions: (1) shorter – compressing lengthy CoTs into concise yet effective reasoning chains; (2) smaller – developing compact language models with strong reasoning capabilities through techniques such as knowledge distillation, other model compression techniques, and reinforcement learning; and (3) faster – designing efficient decoding strategies to accelerate inference of reasoning models.

Submission Length: Long submission (more than 12 pages of main content)

Assigned Action Editor: ~Gunhee_Kim1

Submission Number: 4730