比较推荐系统中不同智能体的选择与聚合，发现逐项聚合比整体选择更有效。
RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation
- 在请求级别选择单一智能体，不如在项目级别学习聚合多个智能体表现。
- 仅用低成本智能体聚合可达到与BM25相当的准确率（HR@10=0.223）。
- 通过门控聚合所有智能体，可在70.2%调用大模型的前提下提升推荐效果。
推荐系统面临多种异构智能体（协同过滤、序列模型、基于内容的检索器、基于LLM的重排序器）的选择难题，但无一智能体始终最优。本文提出RouteRec框架，在电影评分数据集MovieLens-1M上，对比请求级硬选择与项目级学习聚合的性能。全量质量基准显示高潜力（HR@10 = 0.584），但在无泄露的五折交叉验证下，硬选择仍低于BM25（0.223 vs. 0.254），且选择性调用大模型未能改善结果。而项目级聚合则表现更好：仅使用低成本智能体的聚合版本在HR上持平BM25，NDCG点估计达0.123；门控全智能体聚合实现HR@10 = 0.295，同时仅需70.2%的LLM调用。结论是：在稀疏固定候选场景中，请求级单智能体选择过于粗糙，项目级聚合才是更有前景的方向。
原文摘要 · Abstract (English)
Recommender systems increasingly face a choice among heterogeneous agents -- collaborative filters, sequential models, content-based retrievers, and LLM-based rerankers -- yet no single agent is uniformly best. We study this choice as task-aware agent ranking under cost constraints using RouteRec, a framework that compares request-level hard selection with item-level learned aggregation over four traditional recommender agents and one LLM reranker agent. On MovieLens-1M, the full quality oracle has substantial headroom (HR@10 = 0.584), confirming that useful cross-agent signal exists. Under a leakage-free 5-fold out-of-fold protocol, however, hard selection remains below BM25 (0.223 vs. 0.254), and selective LLM escalation does not improve it. The same protocol yields a different outcome for learned aggregation: its cheap-only variant matches BM25 in HR and has a higher NDCG point estimate (0.123 vs. 0.114), while gated all-agent aggregation reaches HR@10 = 0.295 with 70.2\% LLM calls. The resulting lesson is not that routing is solved, but that request-level selection of one complete agent list is too coarse for this sparse fixed-candidate setting; item-level aggregation is the more promising action space.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。