NeuSymMS: A Hybrid Neuro-Symbolic Memory System for Persistent, Self-Curating LLM Agents

TL;DR

NeuSymMS is a hybrid neuro-symbolic memory system that enables LLM agents to learn, remember, and reason across sessions with a structured, scalable, and trustworthy memory architecture.

Contribution

It introduces a novel hybrid neuro-symbolic architecture combining neural fact extraction with a rule-based system for persistent memory management in LLM agents.

Findings

Supports multi-level memory scoping and pruning.

Maintains memory continuity without context bloat.

Offers a practical approach to trustworthy, auditable memory.

Abstract

We present NeuSymMS, an adaptive memory system that enables large language model (LLM) agents to learn, remember, and reason about users across sessions via a hybrid neuro-symbolic architecture. NeuSymMS couples neural fact extraction from unstructured dialogue using LLMs and a CLIPS-based expert system that classifies, deduplicates, and reconciles facts under explicit lifecycle rules. The system represents knowledge as subject-relation-value triples stored in relational database management system. It supports user/agents/agent-to-agent scoping, and implements a dual-horizon (short-term and long-term) memory model. IT leverages access-based promotion and time-based pruning of the memory on both horizpons. NeuSymMS maintains continuity of memory while avoiding context-window bloat and cross-entity contamination. We argue that this architecture offers a practical path to trustworthy, auditable memory for production agentic systems and discuss its novelty relative to log retrieval, summarization, and key-value approaches.