Advancing Multimodal Agent Reasoning with Long-Term Neuro-Symbolic Memory

TL;DR

This paper introduces NS-Mem, a neuro-symbolic long-term memory system for multimodal agents that combines neural and symbolic reasoning to improve accuracy in complex reasoning tasks.

Contribution

The paper presents a novel neuro-symbolic memory framework with a three-layer architecture, automated knowledge consolidation, and hybrid retrieval, enhancing multimodal agent reasoning capabilities.

Findings

Achieves 4.35% higher reasoning accuracy over neural memory systems.

Up to 12.5% improvement on constrained reasoning queries.

Validates effectiveness through real-world multimodal benchmarks.

Abstract

Recent advances in large language models have driven the emergence of intelligent agents operating in open-world, multimodal environments. To support long-term reasoning, such agents are typically equipped with external memory systems. However, most existing multimodal agent memories rely primarily on neural representations and vector-based retrieval, which are well-suited for inductive, intuitive reasoning but fundamentally limited in supporting analytical, deductive reasoning critical for real-world decision making. To address this limitation, we propose NS-Mem, a long-term neuro-symbolic memory framework designed to advance multimodal agent reasoning by integrating neural memory with explicit symbolic structures and rules. Specifically, NS-Mem is operated around three core components of a memory system: (1) a three-layer memory architecture that consists episodic layer, semantic layer and logic rule layer, (2) a memory construction and maintenance mechanism implemented by SK-Gen that automatically consolidates structured knowledge from accumulated multimodal experiences and incrementally updates both neural representations and symbolic rules, and (3) a hybrid memory retrieval mechanism that combines similarity-based search with deterministic symbolic query functions to support structured reasoning. Experiments on real-world multimodal reasoning benchmarks demonstrate that Neural-Symbolic Memory achieves an average 4.35% improvement in overall reasoning accuracy over pure neural memory systems, with gains of up to 12.5% on constrained reasoning queries, validating the effectiveness of NS-Mem.