AI 中文总结
HyperAgent4POI通过动态语义消息传递在多智能体超图中补全缺失模态，在三个LBSN数据集上较15个基线实现排序提升，60%模态缺失率下NDCG@20平均提升8.2%，且推理效率高。
AI 中文摘要
下一个兴趣点（Point-of-Interest, POI）推荐受益于描述场所语义的文本和视觉内容，但这类内容在现实服务中常常不完整。缺失的模态会削弱POI表示，减少排序可用的语义证据，生成的表示也会为高阶用户-POI交互建模提供不可靠的证据。我们提出HyperAgent4POI，该模型采用动态语义消息传递（Dynamic Semantic Message Passing, DSMP）在每个超图层内执行模态补全和软关联细化。持久节点智能体共享一个冻结的Llama主干，并使用角色特定适配器生成节点到超边的消息。由这些消息形成的语义超边 motif 引导软关联评分和模态补全。最终节点表示被缓存用于在线排序，无需调用大语言模型（LLM）。在三个现实世界的基于位置的社交网络（LBSN）数据集上的实验表明，在不同模态缺失率下，该模型相较于15个基线模型均取得了一致的排序提升，同时缓存推理提供了实用的在线效率。在60%的模态缺失率下，HyperAgent4POI在三个数据集上的平均NDCG@20较最强基线提升了8.2%。
英文摘要
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.
