Competence-Aware AI Agents with Metacognition for Unknown Situations and Environments (MUSE)

TL;DR

This paper introduces MUSE, a framework that endows autonomous agents with metacognitive abilities like self-assessment and strategy regulation, significantly improving their adaptability in unfamiliar environments.

Contribution

The paper presents the novel MUSE framework integrating metacognition into autonomous agents, with implementations based on world modeling and large language models.

Findings

MUSE agents outperform traditional methods in novel tasks.

MUSE improves competence awareness and self-regulation.

Framework reduces reliance on extensive training data.

Abstract

Metacognition, defined as the awareness and regulation of one's cognitive processes, is central to human adaptability in unknown situations. In contrast, current autonomous agents often struggle in novel environments due to their limited capacity for adaptation. We hypothesize that metacognition is a critical missing ingredient in autonomous agents for the cognitive flexibility needed to tackle unfamiliar challenges. Given the broad scope of metacognitive abilities, we focus on competence awareness and strategy selection. To this end, we propose the Metacognition for Unknown Situations and Environments (MUSE) framework to integrate metacognitive processes of self-assessment and self-regulation into autonomous agents. We present two implementations of MUSE: one based on world modeling and another leveraging large language models (LLMs). Our system continually learns to assess its competence on a given task and uses this self-assessment to guide iterative cycles of strategy selection. MUSE agents demonstrate high competence awareness and significant improvements in self-regulation for solving novel, out-of-distribution tasks more effectively compared to model-based reinforcement learning and purely prompt-based LLM agent approaches. This work highlights the promise of approaches inspired by cognitive and neural systems in enabling autonomous agents to adapt to new environments while mitigating the heavy reliance on extensive training data and large models for the current models.