#computational-cost2 articles

2 articles

AIBullisharXiv – CS AI · 4h ago2

🧠

Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs

Researchers propose Draft-Thinking, a new approach to improve the efficiency of large language models' reasoning processes by reducing unnecessary computational overhead. The method achieves an 82.6% reduction in reasoning budget with only a 2.6% performance drop on mathematical problems, addressing the costly overthinking problem in current chain-of-thought reasoning.

AIBullisharXiv – CS AI · 4h ago1

🧠

Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning

Researchers developed SWAP (Step-wise Adaptive Penalization), a new AI training method that makes large reasoning models more efficient by reducing unnecessary steps in chain-of-thought reasoning. The technique reduces reasoning length by 64.3% while improving accuracy by 5.7%, addressing the costly problem of AI models 'overthinking' during problem-solving.