arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2602.11516cs.AI
收藏

启发式连续学习内部推理过程：学习如何思考以实现自适应AI系统

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

School of Computer Science, Chengdu University of information Technology（信息科技大学计算机学院）

Hong Su

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种受人类启发的连续学习框架，通过统一推理、行动、反思和验证，实现AI系统在动态环境中的持续适应与自我进化。

摘要：

学习内部推理过程对于开发能够持续适应动态真实环境的AI系统至关重要。然而，大多数现有方法主要强调学习任务特定的输出或静态知识表示，而忽视了内部推理结构、行动调度策略和学习机制本身的连续优化。在本文中，我们提出了一种受人类启发的连续学习框架，该框架在一个通过并行学习增强的顺序推理模型中统一了推理、行动、反思和验证。该框架明确地将内部思维过程作为主要的学习对象。它系统地记录内部推理轨迹和环境互动作为结构化的学习材料，使系统能够优化不仅任务层面的内容，还有推理活动的组织、调度和进化。这种设计实现了学习与处理的同时进行，使认知结构在执行过程中得到改善。此外，该框架支持对预定义逻辑的受控替换，引入了分层学习-学习机制，共同适应任务层面的参数和学习策略。结果，系统在保持操作稳定性的同时逐步进化其内部认知架构。在温度传感器异常检测任务中的实验结果表明，结合内部过程学习可将平均运行时间减少23.9%。

英文摘要：

Learning internal reasoning processes is crucial for developing AI systems capable of sustained adaptation in dynamic real-world environments. However, most existing approaches primarily emphasize learning task-specific outputs or static knowledge representations, while overlooking the continuous refinement of internal reasoning structures, action scheduling policies, and learning mechanisms themselves. In this paper, we propose a human-inspired continuous learning framework that unifies reasoning, action, reflection, and verification within a sequential reasoning model enhanced by parallel learning. The framework explicitly treats internal thinking processes as primary learning objects. It systematically records internal reasoning trajectories and environmental interactions as structured learning material, enabling the system to optimize not only task-level content but also the organization, scheduling, and evolution of reasoning activities. This design realizes learning alongside processing, allowing cognitive structures to improve during execution. Furthermore, the framework supports controlled replacement of predefined logic with learned procedures and introduces a hierarchical learning-to-learn mechanism that jointly adapts task-level parameters and learning strategies. As a result, the system progressively evolves its internal cognitive architecture while preserving operational stability. Experimental results on a temperature sensor abnormality detection task show that incorporating internal-process learning reduces average runtime by 23.9%.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑