Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models
South China University of Technology(南方科技大学);Pazhou Laboratory(琶洲实验室);Peng Cheng Laboratory(鹏城实验室);Chongqing University of Posts and Telecommunications(重庆邮电大学)
Jinwu Hu, Dongjin Yang, Langyu Bian, Zhiquan Wen, Yufeng Wang, Yaofo Chen, Bin Xiao, Yuanqing Li, Mingkui Tan
Large language models (LLMs) have demonstrated impressive performance across various language tasks. However, existing LLM reasoning strategies mainly rely on the LLM itself with fast or slow mode (like o1 thinking) and thus struggle to balance reasoning efficiency and accuracy across queries of varying difficulties. In this paper, we propose Cognitive-Inspired Elastic Reasoning (CogER), a framework inspired by human hierarchical reasoning that dynamically selects the most suitable reasoning strategy for each query. Specifically, CogER first assesses the complexity of incoming queries and assigns them to one of several predefined levels, each corresponding to a tailored processing strategy, thereby addressing the challenge of unobservable query difficulty. To achieve automatic strategy selection, we model the process as a Markov Decision Process and train a CogER-Agent using reinforcement learning. The agent is guided by a reward function that balances solution quality and computational cost, ensuring resource-efficient reasoning. Moreover, for queries requiring external tools, we introduce Cognitive Tool-Assisted Reasoning, which enables the LLM to autonomously invoke external tools within its chain-of-thought. Extensive experiments demonstrate that CogER outperforms state-of-the-art Test-Time scaling methods, achieving at least a 13% relative improvement in average exact match on In-Domain tasks and an 8% relative gain on Out-of-Domain tasks.
Cog-TiPRO: Iterative Prompt Refinement with LLMs to Detect Cognitive Decline via Longitudinal Voice Assistant Commands
Computer Science, University of Massachusetts, Boston, MA, USA(计算机科学,马萨诸塞大学,波士顿,马萨诸塞州,美国);School of Medicine, University of North Carolina, Chapel Hill, NC, USA(医学院,北卡罗来纳大学,夏洛特,北卡罗来纳州,美国)
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
System 0/1/2/3: Quad-process theory for multi-timescale embodied collective cognitive systems
Kyoto University(京都大学);Ritsumeikan University(立命馆大学);Keio University(Keio大学);The University of Tokyo(东京大学);Osaka University(大阪大学);OMRON SINIC X Corporation(OMRON SINIC X公司)
本文提出 System 0/1/2/3 框架,将双过程理论扩展为包含具身过程与集体智能的四过程认知模型,结合多尺度时间理论统一认知动态,为认知科学、AI 和机器人研究提供新理论基础。
DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual-Systems
Shanghai Jiao Tong University(上海交通大学);Beihang University(北京航空航天大学);Stanford University(斯坦福大学);University of Sydney(悉尼大学);SIAT, CAS(中国科学院上海硅酸盐研究所);Beijing Institute of Graphic Communication(北京印刷学院)
Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment
Beijing Normal-Hong Kong Baptist University(北京师范大学-香港浸会大学联合国际学院);Institute of Artificial Intelligence and Future Networks, Beijing Normal University (Zhuhai)(北京师范大学(珠海)人工智能与未来网络研究院);The Hong Kong Polytechnic University(香港理工大学)