Metraipolis › archive › dc_3d75ade2c0cd

Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search — arXiv:2609.30177

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.30177
License (as archived): CC0-1.0
Archived: 2026-10-08T04:26:32.096Z
SHA-256 of the archived text: 8f30e4fd2d6307157570247102e9764c48ae85fd06fa65d9184053572a291791
Stable URL of this page: https://metraipolis.com/documento/dc_3d75ade2c0cd

How to cite

Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search — arXiv:2609.30177 — arXiv (en), https://arxiv.org/abs/2609.30177 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d75ade2c0cd (Metraipolis archive dc_3d75ade2c0cd, sha256 8f30e4fd2d6307157570247102e9764c48ae85fd06fa65d9184053572a291791)

BibTeX

@misc{dc3d75ade2c0cd,
  title = {Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search — arXiv:2609.30177},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30177},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d75ade2c0cd; sha256 8f30e4fd2d6307157570247102e9764c48ae85fd06fa65d9184053572a291791},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30177. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Query understanding (QU) plays a critical role in production search systems, translating raw user queries into search execution plans that drive downstream retrieval and ranking. While large language models (LLMs) have enabled QU to be framed as a structured multi-task generation problem (e.g., intent classification, query expansion), optimizing such models to produce search-engine-coupled outputs remains challenging: static, label-based supervision fails to capture how each component actually interacts with the underlying search pipeline to affect downstream performance. We present a search-aware reinforcement learning (RL) framework for QU based on a distill-then-RL paradigm. Teacher-student supervised fine-tuning (SFT) first yields a well-formed, schema-compliant policy initialization. The RL stage then optimizes each QU component with rewards derived from live interaction with the search engine, tailored to that component's operational role, rather than a single reward tied to the final search outcome. Experiments on Roblox search show that this component-specific optimization improves both per-component utility and downstream search quality, raising NDCG@20 by 8.9 points over the SFT policy and by 3.5 points over training with a single end-to-end reward.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.30177 — 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 2026-10-08T03:50:57.886Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).