Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement

ACL ARR 2026 January Submission5755 Authors

Keywords: LLM agents, self-evolving agents, Meta-learning, Error analysis

Abstract: 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 with 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. Code are available at https://anonymous.4open.science/r/MARS-9F16

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: AI / LLM Agents, Language Modeling, Efficient/Low-Resource Methods for NLP

Contribution Types: NLP engineering experiment, Approaches to low-resource settings, Approaches low compute settings-efficiency, Data analysis

Languages Studied: English

Submission Number: 5755