AIJun 3, 2025

OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation

arXiv:2506.02397v217 citationsh-index: 18Has Code
Originality Incremental advance
AI Analysis

This addresses efficiency issues in reasoning models for AI practitioners by providing an incremental improvement to mitigate unnecessary computational overhead.

The paper tackles the problem of over-reasoning in large reasoning models by introducing OThink-R1, a method that dynamically switches between fast and slow thinking modes to prune redundant reasoning steps, reducing redundancy by almost 23% on average without accuracy loss.

Recent advanced large reasoning models (LRMs) leverage extended chain-of-thought (CoT) reasoning to solve complex tasks, achieving state-of-the-art performance. Despite their success, we identify a critical issue: a substantial portion of simple tasks solved by LRMs can also be addressed by non-reasoning LLMs using significantly fewer tokens, indicating the complex reasoning may not always be necessary. To address this, we systematically analyze the reasoning trajectories of LRMs and present a method utilizing identified paradigms and LLM-Judge to classify these trajectories as either Redundant Reasoning or Essential Reasoning. And we introduce OThink-R1, a method that prunes redundant reasoning steps while preserving logical validity. OThink-R1 dynamically employs the non-thinking mode (fast-thinking) for straightforward problems while engaging in deliberate thinking (slow-thinking) for complex problems. Experiments across mathematical and question-answering tasks demonstrate that OThink-R1 reduces reasoning redundancy by almost 23\% on average without compromising accuracy, offering practical guidelines for efficient reasoning models. The code is available at https://github.com/AgenticIR-Lab/OThink-R1.

Code Implementations1 repo
Foundations

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

Your Notes