AIJun 17, 2024

Metacognitive AI: Framework and the Case for a Neurosymbolic Approach

arXiv:2406.12147v112 citations
Originality Synthesis-oriented
AI Analysis

This is a conceptual position paper proposing a framework for metacognitive AI, which is incremental as it builds on existing ideas without presenting new empirical results.

The paper introduces a framework called TRAP for metacognitive AI, exploring how neurosymbolic AI can address challenges in enabling AI to reason about its own processes.

Metacognition is the concept of reasoning about an agent's own internal processes and was originally introduced in the field of developmental psychology. In this position paper, we examine the concept of applying metacognition to artificial intelligence. We introduce a framework for understanding metacognitive artificial intelligence (AI) that we call TRAP: transparency, reasoning, adaptation, and perception. We discuss each of these aspects in-turn and explore how neurosymbolic AI (NSAI) can be leveraged to address challenges of metacognition.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes