{"slug": "routerec-strict-evaluation-of-recommender-agent-selection-and-aggregation", "title": "RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation", "summary": "Researchers introduced RouteRec, a framework for evaluating recommender-agent selection and aggregation under cost constraints, finding that item-level learned aggregation outperforms request-level hard selection on MovieLens-1M, with gated all-agent aggregation achieving HR@10 = 0.295 using 70.2% LLM calls, while hard selection remains below the BM25 baseline.", "body_md": "arXiv:2607.09908v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/routerec-strict-evaluation-of-recommender-agent-selection-and-aggregation", "canonical_source": "https://arxiv.org/abs/2607.09908", "published_at": "2026-07-14 04:00:00+00:00", "updated_at": "2026-07-14 04:33:25.384427+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-agents"], "entities": ["RouteRec", "MovieLens-1M", "BM25"], "alternates": {"html": "https://wpnews.pro/news/routerec-strict-evaluation-of-recommender-agent-selection-and-aggregation", "markdown": "https://wpnews.pro/news/routerec-strict-evaluation-of-recommender-agent-selection-and-aggregation.md", "text": "https://wpnews.pro/news/routerec-strict-evaluation-of-recommender-agent-selection-and-aggregation.txt", "jsonld": "https://wpnews.pro/news/routerec-strict-evaluation-of-recommender-agent-selection-and-aggregation.jsonld"}}