paper-with-me

Papers

Adaptive Deep Reasoning: Triggering Deep Thinking When Needed

2025-05-26 · Yunhao Wang, Yuhao Zhang, TingHao Yu, Can Xu, Feng Zhang, Fengzong Lian

Large language models (LLMs) have shown impressive capabilities in handling complex tasks through long-chain reasoning. However, the extensive reasoning steps involved can significantly increase computational costs, posing challenges for real-world deployment. Recent efforts have focused on optimizing reasoning efficiency by shortening the Chain-of-Thought (CoT) reasoning processes through various approaches, such as length-aware prompt engineering, supervised fine-tuning on CoT data with variable lengths, and reinforcement learning with length penalties. Although these methods effectively reduce reasoning length, they still necessitate an initial reasoning phase. More recent approaches have attempted to integrate long-chain and short-chain reasoning abilities into a single model, yet they still rely on manual control to toggle between short and long CoT. In this work, we propose a novel approach that autonomously switches between short and long reasoning chains based on problem complexity. Our method begins with supervised fine-tuning of the base model to equip both long-chain and short-chain reasoning abilities. We then employ reinforcement learning to further balance short and long CoT generation while maintaining accuracy through two key strategies: first, integrating reinforcement learning with a long-short adaptive group-wise reward strategy to assess prompt complexity and provide corresponding rewards; second, implementing a logit-based reasoning mode switching loss to optimize the model's initial token choice, thereby guiding the selection of the reasoning type. Evaluations on mathematical datasets demonstrate that our model can dynamically switch between long-chain and short-chain reasoning modes without substantially sacrificing performance. This advancement enhances the practicality of reasoning in large language models for real-world applications.

📄 PDF Abstract BibTeX arXiv:2505.20101

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineeringreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

2025-05-17 · Chenwei Lou, Zewei Sun, Xinnian Liang, Meng Qu 외

Large Language Models (LLMs) have demonstrated remarkable capabilities but often face challenges with tasks requiring sophisticated reasoning. While Chain-of-Thought (CoT) prompting significantly enhances reasoning, it i…

Reinforcement Learning (RL)

Think When You Need: Self-Adaptive Chain-of-Thought Learning

2025-04-04 · Junjie Yang, Ke Lin, Xing Yu

Chain of Thought (CoT) reasoning enhances language models' performance but often leads to inefficient "overthinking" on simple problems. We identify that existing approaches directly penalizing reasoning length fail to a…

MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy

2026-06-26 · Zhiyuan Han, Beier Zhu, Wenwen Tong, Chengwei Qin 외 arxiv

We find that explicit reasoning does not necessarily translate into better multimodal emotion recognition (MER) accuracy, even though it makes predictions more interpretable. Specifically, for reasoning-based MLLMs, fast…

Multimodal Emotion RecognitionReinforcement Learning

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning

2025-05-21 · Xiaoyun Zhang, Jingqing Ruan, Xing Ma, Yawen Zhu 외

Large reasoning models (LRMs) achieve remarkable performance via long reasoning chains, but often incur excessive computational overhead due to redundant reasoning, especially on simple tasks. In this work, we systematic…

Answer Generation

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning

2025-05-21 · Rongzhi Zhu, Yi Liu, Zequn Sun, Yiwei Wang 외

Large reasoning models (LRMs) have significantly advanced performance on complex tasks, yet their tendency to overthink introduces inefficiencies. This study investigates the internal mechanisms of reinforcement learning…

Reinforcement Learning (RL)