让大模型像人一样反思，一次迭代就能高效自我改进。
Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement
- 借鉴教育心理学，融合原则与步骤双重反思机制。
- 单次循环完成优化，计算成本比现有方法降低超50%。
- 适合需要低延迟自进化能力的智能体系统使用。
大型语言模型虽能实现复杂自主行为，但当前智能体仍受限于静态的人工设计提示，难以适应变化。现有自改进框架多依赖高成本的多轮递归循环。为此，我们提出元认知智能体反思自进化框架（MARS），在单次递归周期内实现高效自演化。受教育心理学启发，MARS通过原则性反思（抽象规范规则以避免错误）和程序性反思（提炼成功步骤策略）模拟人类学习过程。将两类洞察整合为优化指令，使智能体无需持续在线反馈即可系统性改进推理逻辑。六项基准测试显示，MARS在性能上超越现有最先进自进化系统，同时显著降低计算开销。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。