Imagen de Portada

Human-Inspired Continuous Learning of Internal Reasoning Processes: Learning How to Think for Adaptive AI Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Su, Hong
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Human Simulation Computation: A Human-Inspired Framework for Adaptive AI Systems
por: Su, Hong
Publicado: (2026)

Human-Inspired Learning for Large Language Models via Obvious Record and Maximum-Entropy Method Discovery
por: Su, Hong
Publicado: (2025)

Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systems
por: Su, Hong
Publicado: (2026)

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
por: Zhang, Xiaoyun, et al.
Publicado: (2025)

How Clinicians Think and What AI Can Learn From It
por: Sengupta, Dipayan, et al.
Publicado: (2026)

Active Thinking Model: A Goal-Directed Self-Improving Framework for Real-World Adaptive Intelligence
por: Su, Hong
Publicado: (2025)

Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought
por: Xiang, Violet, et al.
Publicado: (2025)

Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning
por: Yang, Dongchao, et al.
Publicado: (2025)

Nice Fold or Hero Call: Learning Budget-Efficient Thinking for Adaptive Reasoning
por: Zhou, Zhaomeng, et al.
Publicado: (2026)

Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems
por: Zhao, Haodong, et al.
Publicado: (2025)

Base Models Know How to Reason, Thinking Models Learn When
por: Venhoff, Constantin, et al.
Publicado: (2025)

Reasoning Before Diagnosis: Physician-Inspired Structured Thinking for ECG Classification
por: Wu, Yang, et al.
Publicado: (2026)

From <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization
por: Wang, Beining, et al.
Publicado: (2025)

Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning
por: Xiang, Violet, et al.
Publicado: (2025)

System 2 Reasoning for Human-AI Alignment: Generality and Adaptivity via ARC-AGI
por: Kim, Sejin, et al.
Publicado: (2024)

Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
por: Damani, Mehul, et al.
Publicado: (2024)

Teaching AI to Remember: Insights from Brain-Inspired Replay in Continual Learning
por: Kim, Jina
Publicado: (2025)

NeuroHex: A Brain-Inspired Hex Coordinate System to Enable Highly Computationally-Efficient World Models for Continuous Online-Adaptive Learning
por: Jacobson, Quinn, et al.
Publicado: (2026)

Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models
por: Liu, Yongjiang, et al.
Publicado: (2025)

Adaptive Dual Reasoner: Large Reasoning Models Can Think Efficiently by Hybrid Reasoning
por: Zhang, Yujian, et al.
Publicado: (2025)

Autonomous Question Formation for Large Language Model-Driven AI Systems
por: Su, Hong
Publicado: (2026)

HiCL: Hippocampal-Inspired Continual Learning
por: Kapoor, Kushal, et al.
Publicado: (2025)

Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process
por: Xiao, Tong, et al.
Publicado: (2024)

Thought Cloning: Learning to Think while Acting by Imitating Human Thinking
por: Hu, Shengran, et al.
Publicado: (2023)

Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization
por: Yu, Zishun, et al.
Publicado: (2025)

Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning
por: Ding, Fei, et al.
Publicado: (2026)

Human-Inspired Framework to Accelerate Reinforcement Learning
por: Beikmohammadi, Ali, et al.
Publicado: (2023)

Human-Inspired Multi-Level Reinforcement Learning
por: Wu, Mingkang, et al.
Publicado: (2025)

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
por: Liao, Yi, et al.
Publicado: (2025)

How To Think About End-To-End Encryption and AI: Training, Processing, Disclosure, and Consent
por: Knodel, Mallory, et al.
Publicado: (2024)

InqEduAgent: Adaptive AI Learning Partners with Gaussian Process Augmentation
por: Yang, Wen-Xi, et al.
Publicado: (2025)

AdaptThink: Reasoning Models Can Learn When to Think
por: Zhang, Jiajie, et al.
Publicado: (2025)

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
por: Aggarwal, Pranjal, et al.
Publicado: (2025)

Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning
por: Yang, Wei, et al.
Publicado: (2026)

Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvement
por: Su, Hong
Publicado: (2025)

PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs
por: Margapuri, Venkat, et al.
Publicado: (2025)

Personalized Artificial General Intelligence (AGI) via Neuroscience-Inspired Continuous Learning Systems
por: Gupta, Rajeev, et al.
Publicado: (2025)

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model
por: Wan, Xu, et al.
Publicado: (2025)

CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning
por: Gan, Zeyu, et al.
Publicado: (2025)

Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
por: Su, DiJia, et al.
Publicado: (2024)