Metraipolis › archive › dc_06132f6ec577

EvoRec: A Unified Self-Evolving Agentic Recommender with Dynamic Reflection Trees — arXiv:2611.01977

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01977
License (as archived)
CC0-1.0
Archived
2026-11-03T18:52:45.680Z
SHA-256 of the archived text
11082a63d1c923f66388daa23b22ecad0a78e3543e6379d97de59e0c91b009af
Stable URL of this page
https://metraipolis.com/documento/dc_06132f6ec577

How to cite

EvoRec: A Unified Self-Evolving Agentic Recommender with Dynamic Reflection Trees — arXiv:2611.01977 — arXiv (en), https://arxiv.org/abs/2611.01977 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_06132f6ec577 (Metraipolis archive dc_06132f6ec577, sha256 11082a63d1c923f66388daa23b22ecad0a78e3543e6379d97de59e0c91b009af)
BibTeX
@misc{dc06132f6ec577,
  title = {EvoRec: A Unified Self-Evolving Agentic Recommender with Dynamic Reflection Trees — arXiv:2611.01977},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01977},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_06132f6ec577; sha256 11082a63d1c923f66388daa23b22ecad0a78e3543e6379d97de59e0c91b009af},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01977. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conventional recommender systems rely on fixed cascaded pipelines, limiting their ability to adapt to evolving user needs and feedback. Existing agentic recommenders introduce reasoning and tool use but often lack end-to-end decision control and systematic failure reflection. We propose EvoRec, a unified agentic recommendation framework that combines autonomous decision-making with reflection-driven self-evolution. A Need Agent infers user needs from long-term, short-term, and working memory. A Planning Agent adaptively allocates retrieval budgets between Behavior Continuation and Need Satisfaction, selects retrieval tools, and sets ranking-fusion weights. An Acting Executor executes the plan and records decision traces. Following user feedback, a Dynamic Reflection Tree identifies failures in need inference, planning, or previous repairs, proposes personalized corrections, and validates them through replay. Verified repairs update working memory and are distilled into reusable cross-user strategies, enabling continual improvement without parameter updates. Experiments on a Kuaishou local-services advertising dataset show a 15.7% Hit@50 improvement over the strongest baseline. Hierarchical reflection further improves Hit@50 by 13.1% among users with prior repairs. In a seven-day online A/B test, nearline EvoRec increases advertising revenue by 4.6% and CTCVR by 3.5%, with a 14.5% revenue gain for high-intent users. These results demonstrate the effectiveness of reflection-driven self-evolution in industrial-scale recommendation.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2611.01977 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:16:37.712Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).