arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.06405cs.IR
收藏

TOOL4POI: 一种增强工具的LLM框架用于下一步POI推荐

TOOL4POI: A Tool-Augmented LLM Framework for Next POI Recommendation

Dongsheng Wang, Shen Gao, Chengrui Huang, Yuxi Huang, Ruixiang Feng, Shuo Shang

AI总结:

Tool4POI通过外部检索和推理提升POI推荐性能,无需微调即可兼容现成LLM,实现对OOH场景的显著改进。

摘要:

下一步兴趣点(POI)推荐是基于位置的服务中的基本任务。尽管最近的进展利用大语言模型(LLM)进行序列建模,但现有的基于LLM的方法面临两个关键限制:(i)对用户历史的上下文完整性的强依赖,导致在超出历史(OOH)场景中表现不佳;(ii)由于LLM的限制性上下文窗口,扩展性有限,限制了它们访问和处理大量候选POI的能力。为了解决这些挑战,我们提出了Tool4POI,一种新的增强工具的框架,使LLM能够通过外部检索和推理进行开放集POI推荐。Tool4POI由三个关键模块组成:偏好提取模块、多轮候选检索模块和重排序模块,它们共同总结长期用户兴趣,与外部工具交互以检索相关POI,并根据最近行为优化最终推荐。与现有方法不同,Tool4POI不需要任务特定的微调,并且可以与现成的LLM以即插即用的方式兼容。在三个真实世界数据集上的广泛实验表明,Tool4POI在挑战性的OOH场景中显著优于最先进的基线,实现高达40%的准确率,其中现有方法失败,同时在Acc@5和Acc@10上分别实现平均改进20%和30%。

英文摘要:

Next Point-of-Interest (POI) recommendation is a fundamental task in location-based services. While recent advances leverage Large Language Model (LLM) for sequential modeling, existing LLM-based approaches face two key limitations: (i) strong reliance on the contextual completeness of user histories, resulting in poor performance on out-of-history (OOH) scenarios; (ii) limited scalability, due to the restricted context window of LLMs, which limits their ability to access and process a large number of candidate POIs. To address these challenges, we propose Tool4POI, a novel tool-augmented framework that enables LLMs to perform open-set POI recommendation through external retrieval and reasoning. Tool4POI consists of three key modules: preference extraction module, multi-turn candidate retrieval module, and reranking module, which together summarize long-term user interests, interact with external tools to retrieve relevant POIs, and refine final recommendations based on recent behaviors. Unlike existing methods, Tool4POI requires no task-specific fine-tuning and is compatible with off-the-shelf LLMs in a plug-and-play manner. Extensive experiments on three real-world datasets show that Tool4POI substantially outperforms state-of-the-art baselines, achieving up to 40% accuracy on challenging OOH scenarios where existing methods fail, and delivering average improvements of 20% and 30% on Acc@5 and Acc@10, respectively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑