Agentic Recommender System with Hierarchical Belief-State Memory

• URL: http://arxiv.org/abs/2605.14401v2
• Date: Fri, 15 May 2026 02:07:22 GMT
• Title: Agentic Recommender System with Hierarchical Belief-State Memory
• Abstract summary: We propose a framework that treats recommendation as a partially observable problem and maintains a structured belief state that abstracts noisy behavioral observations into a compact estimate of user preferences.<n>A complete lifecycle of six operations is organized 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 narrative.<n>Experiments 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
• Score: 29.122434746467544
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents [13.846550145896314]
  Memory-augmented LLM agents tackle complex long-horizon tasks by summarizing interaction trajectories into compact memory.<n>Existing approaches typically train these memory policies using outcome-based reinforcement learning, failing to localize where intermediate memory quality degrades.<n>We argue that memory optimization should focus not merely on trajectory-level success, but on the clarity of the belief induced by intermediate summaries.
  arXiv  Detail & Related papers  (2026-05-28T16:17:19Z)
• Rethinking Memory as Continuously Evolving Connectivity [63.58181883607843]
  Existing memory-augmented LLM agents treat memory as a static repository with pre-defined representations and fixed retrieval pipelines.<n>We propose FluxMem, a connectivity-evolving memory framework that models memory as a heterogeneous graph and progressively refines its topology through three stages.<n>Across three fundamentally distinct benchmarks including LoCoMo, Mind2Web, and GAIA, FluxMem achieves consistent state-of-the-art performance, demonstrating strong adaptation and generalization in complex agentic environments.
  arXiv  Detail & Related papers  (2026-05-27T17:35:34Z)
• Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory [53.8372503928207]
  Large language model (LLM) agents require long-term user memory for consistent personalization.<n>Existing memory systems mainly rely on static, hand-crafted update rules.<n>We introduce MemCoE, a cognition-inspired two-stage optimization framework that learns how memory should be organized and what information to update.
  arXiv  Detail & Related papers  (2026-05-01T14:45:20Z)
• Prism: An Evolutionary Memory Substrate for Multi-Agent Open-Ended Discovery [0.0]
  We introduce prism (textbfProbabilistic replicatextbfRetrieval with textbfInformation-textbfStratified textbfMemory), an evolutionary memory substrate for multi-agent AI systems.<n>prism unifies four independently developed paradigms -- layered file-based persistence, vector-augmented semantic memory, graph-structured relational memory, and multi-agent evolutionary search.
  arXiv  Detail & Related papers  (2026-04-08T09:16:43Z)
• AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment [54.72137309071243]
  AlpsBench comprises 2,500 long-term interaction sequences curated from WildChat, paired with human-verified structured memories.<n>We define four pivotal tasks - personalized information extraction, updating, retrieval, and utilization - and establish protocols to evaluate the entire lifecycle of memory management.<n>Our benchmarking of frontier LLMs and memory-centric systems reveals that: (i) models struggle to reliably extract latent user traits; (ii) memory updating faces a performance ceiling even in the strongest models; (iii) retrieval accuracy declines sharply in the presence of large distractor pools; and (iv) while explicit memory mechanisms improve recall, they do not
  arXiv  Detail & Related papers  (2026-03-09T11:06:19Z)
• AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations [61.6579785305668]
  AMemGym is an interactive environment enabling on-policy evaluation and optimization for memory-driven personalization.<n>Our framework provides a scalable, diagnostically rich environment for advancing memory capabilities in conversational agents.
  arXiv  Detail & Related papers  (2026-03-02T15:15:11Z)
• UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory [46.87954895079213]
  Self-evolving memory serves as the trainable parameters for Large Language Models (LLMs)<n>Existing methods predominately optimize memory management while treating memory extraction as a static process.<n>We propose Unified Memory Extraction and Management (UMEM) to jointly optimize a Large Language Model to simultaneous extract and manage memories.
  arXiv  Detail & Related papers  (2026-02-11T08:58:41Z)
• MALLOC: Benchmarking the Memory-aware Long Sequence Compression for Large Sequential Recommendation [84.53415999381203]
  MALLOC is a benchmark for memory-aware long sequence compression.<n>It is integrated into state-of-the-art recommenders, enabling a reproducible and evaluation platform.
  arXiv  Detail & Related papers  (2026-01-28T04:11:50Z)
• MemRec: Collaborative Memory-Augmented Agentic Recommender System [57.548438733740504]
  We propose MemRec, a framework that architecturally decouples reasoning from memory management.<n>MemRec introduces a dedicated LM_Mem to manage a dynamic collaborative memory graph.<n>It achieves state-of-the-art performance on four benchmarks.
  arXiv  Detail & Related papers  (2026-01-13T18:51:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.