NeuSymMS: A Hybrid Neuro-Symbolic Memory System for Persistent, Self-Curating LLM Agents
This work addresses the need for trustworthy, auditable, and persistent memory in production LLM agents, offering a practical alternative to existing log retrieval, summarization, and key-value methods.
NeuSymMS introduces a hybrid neuro-symbolic memory system for LLM agents that extracts facts from dialogue, manages them with an expert system, and stores them as triples in a relational database, enabling persistent, self-curating memory across sessions while avoiding context-window bloat and cross-entity contamination.
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 with 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, supports user/agents/agent-to-agents scoping, and implements a dual-horizon short-term/long-term memory model with access-based promotion and time-based pruning. 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.