Skip to content
AI News HubLIVE
Original source2 min read

RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation

Summary

RouteRec compares request-level hard selection with item-level learned aggregation across four traditional recommender agents and one LLM reranker. Under a leakage-free 5-fold protocol, hard selection underperforms BM25, while gated all-agent aggregation reaches HR@10 0.295 with 70.2% LLM calls, suggesting item-level aggregation is the more promising action space.

SourcearXiv Computational LinguisticsAuthor: Kaiji Zhou, Vladimir Kalmykov, Yue Feng
RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 10 Jul 2026]

Title:RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation

View a PDF of the paper titled RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation, by Kaiji Zhou and 2 other authors

View PDF HTML (experimental)

Abstract: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.

Comments: 8 pages, 7 figures. Accepted at AgentSearch 2026 (The First Workshop on Indexing, Retrieval, and Ranking of AI Agents), co-located with SIGIR 2026

Subjects:

Computation and Language (cs.CL); Information Retrieval (cs.IR)

Cite as: arXiv:2607.09908 [cs.CL]

(or arXiv:2607.09908v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.09908

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Kaiji Zhou [view email] [v1] Fri, 10 Jul 2026 18:58:52 UTC (342 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation, by Kaiji Zhou and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-07

Change to browse by:

cs cs.IR

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Under a leakage-free 5-fold out-of-fold protocol, hard selection (HR@10 0.223) remains below BM25 (0.254), and selective LLM escalation does not improve it.
  • The cheap-only variant of learned aggregation matches BM25 in HR and has a higher NDCG point estimate (0.123 vs. 0.114).
  • Gated all-agent aggregation reaches HR@10 0.295 while invoking the LLM on 70.2% of requests.
  • The full quality oracle reaches HR@10 0.584, confirming substantial headroom from cross-agent signal.

Highlights and analysis are generated automatically and may contain errors. Check the original source.