KIX: A Knowledge and Interaction-Centric Metacognitive Framework for Task Generalization
People aptly exhibit general intelligence behaviors in solving a variety of tasks with flexibility and ability to adapt to novel situations by reusing and applying high-level knowledge acquired over time. But artificial agents are more like specialists, lacking such generalist behaviors. Artificial agents will require understanding and exploiting critical structured knowledge representations. We present a metacognitive generalization framework, Knowledge-Interaction-eXecution (KIX), and argue that interactions with objects leveraging type space facilitate the learning of transferable interaction concepts and generalization. It is a natural way of integrating knowledge into reinforcement learning and is promising to act as an enabler for autonomous and generalist behaviors in artificial intelligence systems.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SCAN: A Decision-Making Framework for Effective Task Allocation with Generative AI
We introduce SCAN -- a human-centric decision-making framework to facilitate learners for effective task allocation with Generative Artificial Intelligence (GenAI) based on Vygotsky's Zone of Proximal Development and Met…
Towards the ISO 24617-2-compliant Typology of Metacognitive Events
The paper presents ongoing efforts in design of a typology of metacognitive events observed in a multimodal dialogue. The typology will serve as a tool to identify relations between participants’ dispositions, dialogue a…
Modeling e-Learners' Cognitive and Metacognitive Strategy in Comparative Question Solving
Cognitive and metacognitive strategy had demonstrated a significant role in self-regulated learning (SRL), and an appropriate use of strategies is beneficial to effective learning or question-solving tasks during a human…
Beyond the Steeper Curve: AI-Mediated Metacognitive Decoupling and the Limits of the Dunning-Kruger Metaphor
The common claim that generative AI simply amplifies the Dunning-Kruger effect is too coarse to capture the available evidence. The clearest findings instead suggest that large language model (LLM) use can improve observ…
Truly Self-Improving Agents Require Intrinsic Metacognitive Learning
Self-improving agents aim to continuously acquire new capabilities with minimal supervision. However, current approaches face two key limitations: their self-improvement processes are often rigid, fail to generalize acro…