Metraipolis › archive › dc_f6875b604d89
PEAR: Progressive Evidence-Based AutoResearch for Industrial Search Systems — arXiv:2609.35031
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35031
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:03:12.432Z
- SHA-256 of the archived text
07792a6bbdf4b8cb1ed830244ce335f6ccf3cc17e2338453f0f51f3a5fab1f6e- Stable URL of this page
https://metraipolis.com/documento/dc_f6875b604d89
How to cite
PEAR: Progressive Evidence-Based AutoResearch for Industrial Search Systems — arXiv:2609.35031 — arXiv (en), https://arxiv.org/abs/2609.35031 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f6875b604d89 (Metraipolis archive dc_f6875b604d89, sha256 07792a6bbdf4b8cb1ed830244ce335f6ccf3cc17e2338453f0f51f3a5fab1f6e)
BibTeX
@misc{dcf6875b604d89,
title = {PEAR: Progressive Evidence-Based AutoResearch for Industrial Search Systems — arXiv:2609.35031},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35031},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f6875b604d89; sha256 07792a6bbdf4b8cb1ed830244ce335f6ccf3cc17e2338453f0f51f3a5fab1f6e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35031. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AutoResearch improves systems through iterative experimentation: agents propose candidate modifications, evaluate them, and use the results to guide subsequent exploration. Applying this paradigm to industrial search presents two challenges. (1) Common AutoResearch approaches follow a keep-if-better rule, retaining the highest-scoring candidate for subsequent experiments. Under non-stationary traffic, transient gains may be mistaken for persistent improvements, impairing reliable accumulation of search knowledge. (2) Candidate modifications can be evaluated at multiple fidelity levels, from low-cost proxies to online validation, differing in cost, objective alignment, and statistical reliability. Existing methods rely on individual signals or task-specific procedures, lacking a unified basis for using evidence across levels to guide search. We introduce Progressive Evidence-Based AutoResearch (PEAR) with two complementary components. Evidence-driven AutoResearch maintains an independent, hypothesis-guided research state for each strategy task within a predefined objective and intervention scope. Each state evolves through a Plan-Execute-Evaluate-Update transition that links experimentation to context-aware evidence interpretation and hypothesis revision. Confidence-Gated Verifier Ladder organizes evaluation into four levels of increasing fidelity: Offline Replay, Shadow-Traffic Evaluation, Rapid Online Evaluation, and Decision-Grade Online Evaluation. A unified confidence-based gate promotes candidates only when evidence supports a statistically significant positive effect, enabling broad low-cost exploration while reserving costly online experiments for promoted candidates. In a real-world industrial search system, strategies optimized with PEAR significantly increased Main Order/DAU by 2.7336% and 3.2957% relative to their respective baselines in two A/B experiments. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.35031 — 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 2026-10-07T20:29:03.238Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).