Agentic Recommender System with Hierarchical Belief-State Memory

TL;DR

MARS is a hierarchical memory framework for recommender systems that models user preferences as a structured belief state, improving personalization by adaptively managing memory lifecycle operations.

Contribution

It introduces a novel hierarchical memory structure and a lifecycle management process for user preferences, guided by an LLM-based planner, advancing personalized recommendation systems.

Findings

Achieves 26.4% improvement in HR@1 over baselines.

Achieves 10.3% improvement in NDCG@10.

State-of-the-art performance on four benchmark domains.

Abstract

Memory-augmented LLM agents have advanced personalized recommendation, yet existing approaches universally adopt flat memory representations that conflate ephemeral signals with stable preferences, and none provides a complete lifecycle governing how memory should evolve. We propose MARS (Memory-Augmented Agentic Recommender System), a framework that treats recommendation as a partially observable problem and maintains a structured belief state that progressively abstracts noisy behavioral observations into a compact estimate of user preferences. MARS organizes this belief state into three tiers: event memory buffers raw signals, preference memory maintains fine-grained mutable chunks with explicit strength and evidence tracking, and profile memory distills all preferences into a coherent natural language narrative. A complete lifecycle of six operations -- extraction, reinforcement, weakening, consolidation, forgetting, and resynthesis -- is adaptively scheduled by an LLM-based planner rather than fixed-interval heuristics. Experiments on four InstructRec benchmark domains show that MARS achieves state-of-the-art performance with average improvements of 26.4% in HR@1 and 10.3% in NDCG@10 over the strongest baselines with further gains from agentic scheduling in evolving settings.