Metraipolis › archive › dc_de07e165e701
A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing — arXiv:2608.04625
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04625
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:12:38.559Z
- SHA-256 of the archived text
99f887892f7f50fb392954b1f4ee49bbdb9cab50c0d1c2716887879bd883b4c9- Stable URL of this page
https://metraipolis.com/documento/dc_de07e165e701
How to cite
A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing — arXiv:2608.04625 — arXiv (en), https://arxiv.org/abs/2608.04625 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de07e165e701 (Metraipolis archive dc_de07e165e701, sha256 99f887892f7f50fb392954b1f4ee49bbdb9cab50c0d1c2716887879bd883b4c9)
BibTeX
@misc{dcde07e165e701,
title = {A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing — arXiv:2608.04625},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04625},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de07e165e701; sha256 99f887892f7f50fb392954b1f4ee49bbdb9cab50c0d1c2716887879bd883b4c9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04625. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Industrial recommendation strategy iteration heavily relies on large-scale A/B experimentation. Traditional tuning requires experts to repeatedly design strategies, configure experiments, analyze results, and adjust parameters, making the process labor-intensive and time-consuming. Meanwhile, valuable knowledge from historical experiments is often fragmented, making systematic reuse difficult through manual expert effort alone. Existing RAG agents partially alleviate this burden by retrieving prior strategies, but typically organize experience in a flat manner, overlooking the hierarchical relationships among business scenarios, recommendation stages, optimization objectives, and experimental contexts. This often results in mismatched retrieval and limited cross-scenario transfer, while preventing agents from continuously refining strategies and parameters through sequential A/B feedback. % To address these limitations, we propose A/B Agent, a closed-loop A/B agent for industrial recommendation strategy optimization. The framework comprises three tightly coupled core components: Historical Strategy Knowledge Organization, Autonomous Target-Aware Strategy Generation, and Experiment-Guided Strategy Self-Evolution. It organizes historical strategies into a hierarchical experience tree, retrieves transferable evidence through multi-path Tree-RAG to generate executable strategies, and continuously analyzes online A/B feedback to guide autonomous tuning and update the experience tree for self-evolution. Extensive offline and online evaluations demonstrate its effectiveness, including a 4.829% improvement in GMV in a real-world short-video e-commerce recommendation system while maintaining positive gains across all guardrail metrics. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.04625 — 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 2026-10-31T11:02:13.417Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).