一作ACL 2026Poster· Natural Language Processing
Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement
Xinmeng Hou · Bohao Qu · Wuqi Wang · Peiliang Gong · Qing Guo · Yang Liu
摘要
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 incu...