Dice Question Streamline Icon: https://streamlinehq.com

Meta-cognitive agents via fusion of cognitive architectures and LLMs

Fuse cognitive architectures such as ACT-R, Soar, or Sigma with large language models to develop meta-cognitive agents capable of self-monitoring, evaluation, and adaptive adjustment of reasoning and learning.

Information Square Streamline Icon: https://streamlinehq.com

Background

The review describes proposals to augment cognitive architectures with LLMs for embodied agents and general intelligence. The authors explicitly mark as open the development of meta-cognitive agents through such fusion.

References

Open research questions remain around how Neuro-Symbolic AI can integrate symbolic reasoning with meta-reinforcement learning for complex decision-making, fuse cognitive architectures with LLMs to develop meta-cognitive agents, leverage LLMs to enhance instance-based learning through meta-cognitive signals, create adaptive meta-cognitive frameworks for real-time conflict resolution, combine modular and agency approaches to build meta-cognitive AI systems aligned with the Common Model of Cognition, improve few-shot learning with cognitive architectures for meta-cognitive awareness, and develop Neuro-Symbolic generative networks that replicate human-like meta-cognitive processes.

Neuro-Symbolic AI in 2024: A Systematic Review (2501.05435 - Colelough et al., 9 Jan 2025) in Section 4.6 Meta-Cognition