Procedural Memory Is Not All You Need: Bridging Cognitive Gaps in LLM-Based Agents

TL;DR

This paper critiques the limitations of LLMs' procedural memory in complex environments and proposes augmenting them with semantic memory and associative learning for more adaptive AI agents.

Contribution

It introduces a modular architecture combining procedural, semantic, and associative memory to enhance LLMs' adaptability in unpredictable settings.

Findings

Procedural memory alone is insufficient for complex, unpredictable tasks.

Augmenting LLMs with semantic and associative memory improves adaptability.

Modular architecture bridges the gap between narrow expertise and general intelligence.

Abstract

Large Language Models (LLMs) represent a landmark achievement in Artificial Intelligence (AI), demonstrating unprecedented proficiency in procedural tasks such as text generation, code completion, and conversational coherence. These capabilities stem from their architecture, which mirrors human procedural memory -- the brain's ability to automate repetitive, pattern-driven tasks through practice. However, as LLMs are increasingly deployed in real-world applications, it becomes impossible to ignore their limitations operating in complex, unpredictable environments. This paper argues that LLMs, while transformative, are fundamentally constrained by their reliance on procedural memory. To create agents capable of navigating ``wicked'' learning environments -- where rules shift, feedback is ambiguous, and novelty is the norm -- we must augment LLMs with semantic memory and associative learning systems. By adopting a modular architecture that decouples these cognitive functions, we can bridge the gap between narrow procedural expertise and the adaptive intelligence required for real-world problem-solving.