Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909993309044736 |
|---|---|
| author | Hou, Xinmeng Gong, Peiliang Qu, Bohao Wang, Wuqi Guo, Qing Liu, Yang |
| author_facet | Hou, Xinmeng Gong, Peiliang Qu, Bohao Wang, Wuqi Guo, Qing Liu, Yang |
| contents | While Large Language Models (LLMs) enable complex autonomous behavior, current agents remain constrained by static, human-designed prompts that limit adaptability. Existing self-improving frameworks attempt to bridge this gap but typically rely on inefficient, multi-turn recursive loops that incur high computational costs. To address this, we propose Metacognitive Agent Reflective Self-improvement (MARS), a framework that achieves efficient self-evolution within a single recurrence cycle. Inspired by educational psychology, MARS mimics human learning by integrating principle-based reflection (abstracting normative rules to avoid errors) and procedural reflection (deriving step-by-step strategies for success). By synthesizing these insights into optimized instructions, MARS allows agents to systematically refine their reasoning logic without continuous online feedback. Extensive experiments on six benchmarks demonstrate that MARS outperforms state-of-the-art self-evolving systems while significantly reducing computational overhead. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11974 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement Hou, Xinmeng Gong, Peiliang Qu, Bohao Wang, Wuqi Guo, Qing Liu, Yang Artificial Intelligence While Large Language Models (LLMs) enable complex autonomous behavior, current agents remain constrained by static, human-designed prompts that limit adaptability. Existing self-improving frameworks attempt to bridge this gap but typically rely on inefficient, multi-turn recursive loops that incur high computational costs. To address this, we propose Metacognitive Agent Reflective Self-improvement (MARS), a framework that achieves efficient self-evolution within a single recurrence cycle. Inspired by educational psychology, MARS mimics human learning by integrating principle-based reflection (abstracting normative rules to avoid errors) and procedural reflection (deriving step-by-step strategies for success). By synthesizing these insights into optimized instructions, MARS allows agents to systematically refine their reasoning logic without continuous online feedback. Extensive experiments on six benchmarks demonstrate that MARS outperforms state-of-the-art self-evolving systems while significantly reducing computational overhead. |
| title | Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.11974 |