REFLEX: Metacognitive Reasoning for Reflective Zero-Shot Robotic Planning with Large Language Models

TL;DR

REFLEX introduces a metacognitive learning framework for large language model-powered robots, enabling reasoning, reflection, and creative problem-solving to improve performance in complex, zero-shot robotic tasks.

Contribution

The paper presents a novel framework that integrates metacognitive capabilities into LLM-based robotic systems, enhancing their ability to reason, reflect, and generate solutions in new scenarios.

Findings

Significant performance improvements over baselines.

Framework enables creative, non-traditional solutions.

Effective in both existing and novel robotic tasks.

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 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 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 REFLEX, a framework that integrates metacognitive learning into LLM-powered multi-robot collaboration. The system 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. We propose a more challenging robotic benchmark task and evaluate our framework on the existing benchmark and the novel task. Experimental results show that our metacognitive learning framework significantly outperforms existing baselines. Moreover, we observe that our framework can generate solutions that differ from the ground truth yet still successfully complete the tasks. These findings support our hypothesis that metacognitive learning can foster creativity in robotic planning.