mlsanityData to 14 Oct 2026

HyperAgent4POI: Dynamic Semantic Message Passing on Multi-Agent Hypergraphs for Missing-Modality Recommendation

arXiv 2608.01846 ↗First posted 3 Aug 2026cs.IRcited by 0

On the map: LLM agents and tool use → Agentic recommender systems

Abstract (arXiv)

Next Point-of-Interest (POI) recommendation benefits from textual and visual content that describes venue semantics, yet such content is often incomplete in real-world services. Missing modalities weaken POI representations and reduce the semantic evidence available for ranking. The resulting representations also provide unreliable evidence for modeling higher-order user--POI interactions. We propose HyperAgent4POI, which uses Dynamic Semantic Message Passing (DSMP) to perform modality completion and soft incidence refinement within each hypergraph layer. Persistent node agents share a frozen Llama backbone and use role-specific adapters to produce node-to-hyperedge messages. Semantic hyperedge motifs formed from these messages guide soft incidence scoring and modality completion. Final node representations are cached for online ranking without LLM calls. Experiments on three real-world LBSN datasets show consistent ranking gains over 15 baselines across modality-missing rates, while cached inference provides practical online efficiency. Under a 60% modality-missing rate, HyperAgent4POI improves NDCG@20 over the strongest baseline by 8.2% on average across the three datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use. Builds on 19 of its 41 references that are in the map. First posted on arXiv 3 Aug 2026.

Builds on

19 of 41 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025A Survey on LLM-powered Agents for Recommender Systems14 Feb
  2. 2024MACRec: a Multi-Agent Collaboration Framework for Recommendation23 Feb

Other references · 17

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  3. 2019Neural Graph Collaborative Filteringcited by 661
  4. 2020Self-supervised Graph Learning for Recommendationcited by 305
  5. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  6. 2023Representation Learning with Large Language Models for Recommendationcited by 155
  7. 2021On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Featurescited by 63
  8. 2020Graph Convolutional Networks for Graphs Containing Missing Featurescited by 47
  9. 2024Learnable Expansion of Graph Operators for Multi-Modal Feature Fusioncited by 23
  10. 2024LLM-Guided Multi-View Hypergraph Learning for Human-Centric Explainable Recommendationcited by 19
  11. 2024A Multimodal Single-Branch Embedding Network for Recommendation in Cold-Start and Missing Modality Scenarioscited by 13
  12. 2025Generating with Fairness: A Modality-Diffused Counterfactual Framework for Incomplete Multimodal Recommendationscited by 13
5 more
  1. 2018LRMM: Learning to Recommend with Missing Modalitiescited by 8
  2. 2023Meta-learning enhanced next POI recommendation by leveraging check-ins from auxiliary citiescited by 6
  3. 2025Disentangling and Generating Modalities for Recommendation in Missing Modality Scenarioscited by 4
  4. 2025Multi-Modal Hypergraph Enhanced LLM Learning for Recommendationcited by 3
  5. 2026Robust Multimodal Recommendation via Graph Retrieval-Enhanced Modality Completioncited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Agent4POI: Agentic Context-Conditioned Affordance Reasoning for Multimodal Point-of-Interest Recommendation
  2. 2025Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation
  3. 2026Meta-Modal Agent: Sequential Evidence Routing for Missing-Modality Candidate Reranking
  4. 2026Agents as Knowledge Integrator and Utilizer in Multimodal Recommendation
  5. 2026AdaM-Rec: Adaptive Modality Routing for Multimodal Recommendation ↗
  6. 2026RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents
  7. 2026Hi-SAM: A Hierarchical Structure-Aware Multi-modal Framework for Large-Scale Recommendation
  8. 2025AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents