Cognitively-Inspired Episodic Memory Architectures for Accurate and Efficient Character AI

TL;DR

This paper introduces a cognitively-inspired episodic memory system for character AI that balances response depth and efficiency, enabling accurate, resource-efficient dialogue and biographical analysis.

Contribution

The authors develop a novel architecture combining offline data augmentation and parallel retrieval from structured memory, improving response quality and speed for character AI.

Findings

Achieves 0.52s prompt generation latency.

Performs on par with GPT-4 RAG on large models.

Outperforms smaller models like GPT-3.5 and GPT-3.

Abstract

Large language models show promise for embodying historical characters in dialogue systems, but existing approaches face a critical trade-off: simple retrieval-augmented generation produces shallow responses, while multi-stage reflection achieves depth at prohibitive latency. We present an architecture that resolves this tension through offline data augmentation and efficient parallel retrieval from structured episodic memory. Our system transforms biographical data into 1,774 enriched first-person memories with affective-semantic metadata, then employs two-stage retrieval achieving 0.52s prompt generation. Evaluation using LLM-as-judge and RAGAs metrics shows our approach achieves parity with traditional RAG on GPT-4 while significantly outperforming it on smaller models (GPT-3.5, GPT-3), suggesting particular value for resource-constrained deployments. Beyond dialogue, the structured memory enables novel visualization tools: spatiotemporal heatmaps, emotional trajectory analysis, and interactive path tracking, positioning the system as both a dialogue interface and research tool for biographical analysis. We use Van Gogh as a test case, but the architecture is generalizable to any historical figure with substantial textual records, offering a practical framework for educational, museum, and research applications requiring both accuracy and efficiency