Metraipolis › archive › dc_0cfcf145c871

Navigating Runtime Dynamism in Semantic Query Serving — arXiv:2611.04248

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04248
License (as archived)
CC0-1.0
Archived
2026-11-04T18:36:33.184Z
SHA-256 of the archived text
258b3aa16d4b52225151db5dd059d496924fda3df7aac51215b2956382e2c26c
Stable URL of this page
https://metraipolis.com/documento/dc_0cfcf145c871

How to cite

Navigating Runtime Dynamism in Semantic Query Serving — arXiv:2611.04248 — arXiv (en), https://arxiv.org/abs/2611.04248 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0cfcf145c871 (Metraipolis archive dc_0cfcf145c871, sha256 258b3aa16d4b52225151db5dd059d496924fda3df7aac51215b2956382e2c26c)
BibTeX
@misc{dc0cfcf145c871,
  title = {Navigating Runtime Dynamism in Semantic Query Serving — arXiv:2611.04248},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04248},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0cfcf145c871; sha256 258b3aa16d4b52225151db5dd059d496924fda3df7aac51215b2956382e2c26c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04248. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-powered semantic queries increasingly combine relational processing with multiple LLM-based operators over unstructured data. Efficiently serving such queries is challenging due to runtime dynamism at two coupled levels. Across queries, dynamic arrivals and heterogeneous resource demands continuously change scheduling priorities. Within a query, heterogeneous characteristics across fine-grained input batches cause operator costs and selectivities to vary throughout execution, making a statically optimized plan unreliable. These two forms of dynamism create a circular dependency: inter-query scheduling requires estimates of remaining LLM work, while the remaining work depends on runtime plan choices whose costs become observable only during execution. We present SeqoFlow, a runtime framework that jointly adapts query plans and schedules concurrent semantic queries. SeqoFlow enumerates equivalence-preserving plan alternatives under operator dependencies and decomposes queries into fine-grained units, enabling safe plan adaptation and query preemption at batch boundaries. To support both decisions without exhaustively profiling candidate plans on the target LLM, SeqoFlow uses lightweight speculative estimation to capture runtime costs. These estimates jointly guide plan adaptation and inter-query scheduling, closing the loop between query optimization and LLM inference. Experiments across diverse query structures, data distributions, and arrival rates show that SeqoFlow substantially reduces end-to-end latency compared to existing semantic query systems, adaptive query processing techniques, and conventional scheduling policies.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Databases (cs.DB) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04248 — 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 2026-11-04T18:32:37.428Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).