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

arXiv: https://arxiv.org/abs/2602.11516 · HTML: https://mlsanity.com/paper/2602.11516/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 15 of its 16 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 15 of 15)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment](https://mlsanity.com/paper/2312.12148/) (2023)
- [Evaluating Step-by-step Reasoning Traces: A Survey](https://mlsanity.com/paper/2502.12289/) (2025)
- [Re-ReST: Reflection-Reinforced Self-Training for Language Agents](https://mlsanity.com/paper/2406.01495/) (2024)
- [Human-Inspired Learning for Large Language Models via Obvious Record and Maximum-Entropy Method Discovery](https://mlsanity.com/paper/2512.12608/) (2025)
- [Actively Obtaining Environmental Feedback for Autonomous Action Evaluation Without Predefined Measurements](https://mlsanity.com/paper/2601.04235/) (2026)
- [Human Simulation Computation: A Human-Inspired Framework for Adaptive AI Systems](https://mlsanity.com/paper/2601.13887/) (2026)

## Built on by (most cited first, 1 of 1)

- [Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systems](https://mlsanity.com/paper/2604.14178/) (2026)

## Abstract (arXiv)

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%.