paper-with-me

Papers

DynamicMind: A Tri-Mode Thinking System for Large Language Models

2025-06-06 · Wei Li, Yanbin Wei, Qiushi Huang, Jiangyue Yan, Yang Chen, James T. Kwok, Yu Zhang

Modern large language models (LLMs) often struggle to dynamically adapt their reasoning depth to varying task complexities, leading to suboptimal performance or inefficient resource utilization. To address this, we introduce DynamicMind, a novel tri-mode thinking system. DynamicMind empowers LLMs to autonomously select between Fast, Normal, and Slow thinking modes for zero-shot question answering (ZSQA) tasks through cognitive-inspired prompt engineering. Our framework's core innovations include: (1) expanding the established dual-process framework of fast and slow thinking into a tri-mode thinking system involving a normal thinking mode to preserve the intrinsic capabilities of LLM; (2) proposing the Thinking Density metric, which aligns computational resource allocation with problem complexity; and (3) developing the Thinking Mode Capacity (TMC) dataset and a lightweight Mind Router to predict the optimal thinking mode. Extensive experiments across diverse mathematical, commonsense, and scientific QA benchmarks demonstrate that DynamicMind achieves superior ZSQA capabilities while establishing an effective trade-off between performance and computational efficiency.

📄 PDF Abstract BibTeX arXiv:2506.05936

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyPrompt EngineeringQuestion Answering

Similar Papers 제목 키워드 기반

Hume: Introducing System-2 Thinking in Visual-Language-Action Model

2025-05-27 · Haoming Song, Delin Qu, Yuanqi Yao, Qizhi Chen 외

Humans practice slow thinking before performing actual actions when handling complex tasks in the physical world. This thinking paradigm, recently, has achieved remarkable advancement in boosting Large Language Models (L…

DenoisingVision-Language-Action

Virgo: A Preliminary Exploration on Reproducing o1-like MLLM

2025-01-03 · Yifan Du, Zikang Liu, YiFan Li, Wayne Xin Zhao 외

Recently, slow-thinking reasoning systems, built upon large language models (LLMs), have garnered widespread attention by scaling the thinking time during inference. There is also growing interest in adapting this capabi…

Language ModelingLanguage ModellingVisual Reasoning

Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models

2025-08-05 · Haotian Wu, Bo Xu, Yao Shu, Menglin Yang 외 arxiv

Reasoning large language models (RLLMs) have recently demonstrated remarkable capabilities through structured and multi-step reasoning. While prior research has primarily focused on improving their training and inference…

ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs

2025-03-17 · Pengcheng Wen, Jiaming Ji, Chi-Min Chan, Juntao Dai 외

Large language models (LLMs) have demonstrated enhanced performance through the \textit{Thinking then Responding} paradigm, where models generate internal thoughts before final responses (aka, System 2 thinking). However…

Instruction Following

S1-Bench: A Simple Benchmark for Evaluating System 1 Thinking Capability of Large Reasoning Models

2025-04-14 · Wenyuan Zhang, Shuaiyi Nie, Xinghua Zhang, Zefeng Zhang 외

We introduce S1-Bench, a novel benchmark designed to evaluate the performance of Large Reasoning Models (LRMs) on simple tasks that favor intuitive system 1 thinking rather than deliberative system 2 reasoning. While LRM…

Natural Questions