NEOLAF, an LLM-powered neural-symbolic cognitive architecture
This addresses the need for explainable and self-improving agents in cognitive architectures and adaptive instructional systems, though it appears incremental as it builds on existing neural-symbolic approaches.
The paper tackles the problem of constructing intelligent agents by proposing NEOLAF, a neural-symbolic cognitive architecture, and demonstrates its superior learning capability on complex math problems from the MATH dataset.
This paper presents the Never Ending Open Learning Adaptive Framework (NEOLAF), an integrated neural-symbolic cognitive architecture that models and constructs intelligent agents. The NEOLAF framework is a superior approach to constructing intelligent agents than both the pure connectionist and pure symbolic approaches due to its explainability, incremental learning, efficiency, collaborative and distributed learning, human-in-the-loop enablement, and self-improvement. The paper further presents a compelling experiment where a NEOLAF agent, built as a problem-solving agent, is fed with complex math problems from the open-source MATH dataset. The results demonstrate NEOLAF's superior learning capability and its potential to revolutionize the field of cognitive architectures and self-improving adaptive instructional systems.