Go to ACL ARR 2025 May homepageThink, Reflect, Create: Metacognitive Learning for Zero-Shot Robotic Planning with LLMs
Abstract: While large language models (LLMs) have shown great potential across various domains, their applications in robotics remain largely limited to static, prompt-based behaviors and still face challenges in handling complex tasks under zero-shot or few-shot settings. Inspired by human metacognitive learning and creative problem-solving, we address this limitation by exploring a fundamental research question: Can LLMs be empowered with metacognitive capabilities to reason, reflect, and create, thereby enhancing their ability to perform robotic tasks with minimal demonstrations? In this paper, we present an early-stage framework that integrates metacognitive learning into LLM-powered multi-robot collaboration. The proposed framework equips the LLM-powered robotic agents with a skill decomposition and self-reflection mechanism that identifies modular skills from prior tasks, reflects on failures in unseen task scenarios, and synthesizes effective new solutions. Experimental results show that our metacognitive-learning-empowered LLM framework significantly outperforms existing baselines. Moreover, we observe that the framework is capable of generating solutions that differ from the ground truth yet still successfully complete the tasks. These exciting findings support our hypothesis that metacognitive learning can foster creativity in robotic planning.
Paper Type: Short
Research Area: Dialogue and Interactive Systems
Research Area Keywords: task-oriented,knowledge augmented,embodied agents
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models, Data analysis, Theory
Languages Studied: English
Keywords: Metacognitive learning, LLM, Robotic Manipulation, Zero-shot Planning, Multi-Robot Collaboration, Skill Decomposition, Self-Reflection
Submission Number: 4628
Loading