Metraipolis › archive › dc_2cc9e595df52
SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations — arXiv:2609.11414
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11414
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:27:03.091Z
- SHA-256 of the archived text
1399b2a5fb54ae2aa83d407799b72bdb79783263aa5d1c71e1d0f2fb84d2106e- Stable URL of this page
https://metraipolis.com/documento/dc_2cc9e595df52
How to cite
SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations — arXiv:2609.11414 — arXiv (en), https://arxiv.org/abs/2609.11414 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2cc9e595df52 (Metraipolis archive dc_2cc9e595df52, sha256 1399b2a5fb54ae2aa83d407799b72bdb79783263aa5d1c71e1d0f2fb84d2106e)
BibTeX
@misc{dc2cc9e595df52,
title = {SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations — arXiv:2609.11414},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11414},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2cc9e595df52; sha256 1399b2a5fb54ae2aa83d407799b72bdb79783263aa5d1c71e1d0f2fb84d2106e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11414. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models exhibit complementary strengths, motivating routing methods that dispatch each query to the most suitable model. Although existing routers are effective in single-turn settings, they do not directly transfer to multi-turn dialogue, where routing performance critically depends on how historical context is segmented, retained, and incorporated into the current prompt. This introduces two fundamental challenges: preventing information loss and information confusion during context construction, and evaluating routing quality without conflating model selection with prompt construction quality. In this paper, we propose SWRouter, a Similarity-Contractive Window Router for multi-turn large language model routing. SWRouter combines a similarity-based context segmentation mechanism for prompt construction with a dual-metric evaluation framework that decouples construction accuracy from router performance. Experiments on multi-turn dialogue benchmarks demonstrate that SWRouter consistently surpasses strong baselines, achieving a 16.26% improvement in evaluation accuracy over the best individual large language model and an additional 8.22% gain over the Conv-ID Context baseline. Our results highlight that multi-turn large language model routing requires a joint design of context construction and evaluation, rather than a direct extension of single-turn routing methods. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.11414 — 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 2026-10-16T05:17:52.165Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).