# Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding

## TL;DR

This paper explores how prompt-level cognitive scaffolds, including symbolic structures and memory, influence the reasoning and instructional behaviors of large language models in dialogue, demonstrating that structured prompts improve model performance.

## Contribution

It introduces a symbolic scaffolding method with memory schemas to enhance LLM reasoning and provides systematic evaluation showing its effectiveness over baseline variants.

## Key findings

- Removing memory degrades reasoning abilities
- Symbolic structure improves adaptive probing
- Full system outperforms baselines in cognitive behaviors

## Abstract

We study how prompt-level inductive biases influence the cognitive behavior of large language models (LLMs) in instructional dialogue. We introduce a symbolic scaffolding method paired with a short-term memory schema designed to promote adaptive, structured reasoning in Socratic tutoring. Using controlled ablation across five system variants, we evaluate model outputs via expert-designed rubrics covering scaffolding, responsiveness, symbolic reasoning, and conversational memory. We present preliminary results using an LLM-based evaluation framework aligned to a cognitively grounded rubric. This enables scalable, systematic comparisons across architectural variants in early-stage experimentation. The preliminary results show that our full system consistently outperforms baseline variants. Analysis reveals that removing memory or symbolic structure degrades key cognitive behaviors, including abstraction, adaptive probing, and conceptual continuity. These findings support a processing-level account in which prompt-level cognitive scaffolds can reliably shape emergent instructional strategies in LLMs.