AICLFeb 28

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

Jie Cao, Tianwei Lin, Zhenxuan Fan, Bo Yuan, Ziyuan Zhao, Rolan Yan, Wenqiao Zhang, Siliang Tang
arXiv:2603.00578v1
Originality Incremental advance
AI Analysis

This addresses efficiency for users of large reasoning models by reducing computational costs, though it is incremental as it builds on existing CoT paradigms.

The paper tackles the problem of high reasoning costs in long chain-of-thought LLMs by proposing Draft-Thinking, which reduces reasoning budget by 82.6% on MATH500 with only a 2.6% performance drop.

Long chain-of-thought~(CoT) has become a dominant paradigm for enhancing the reasoning capability of large reasoning models~(LRMs); however, the performance gains often come with a substantial increase in reasoning budget. Recent studies show that existing CoT paradigms tend to induce systematic overthinking, unnecessarily coupling reasoning capability with reasoning cost. Most prior approaches reduce token usage through post hoc techniques such as token compression, truncation, or length penalties, without explicitly addressing the core mechanisms of reasoning. We propose \textbf{Draft-Thinking}, which guides models to first learn a concise \textit{draft-style} reasoning structure that retains only the critical reasoning steps. Through a \textit{progressive curriculum learning}, the model stably internalizes this efficient reasoning pattern as its capability scales. Moreover, Draft-Thinking introduces adaptive prompting, which elevates reasoning depth to a flexible, model-selectable behavior. Extensive experiments demonstrate that Draft-Thinking substantially reduces reasoning budget while largely preserving reasoning performance; for example, on MATH500, it achieves an 82.6\% reduction in reasoning budget at the cost of only a 2.6\% performance drop.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes