Metraipolis › archive › dc_9ac97f9fbeee
Whose turn is it? Context-guided model routing for stateful agents — arXiv:2610.19292
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19292
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:01:06.706Z
- SHA-256 of the archived text
b6c2fd23ef0aadce588131cf04f92f8466327f46b3fc614fbe012e1a341af23f- Stable URL of this page
https://metraipolis.com/documento/dc_9ac97f9fbeee
How to cite
Whose turn is it? Context-guided model routing for stateful agents — arXiv:2610.19292 — arXiv (en), https://arxiv.org/abs/2610.19292 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ac97f9fbeee (Metraipolis archive dc_9ac97f9fbeee, sha256 b6c2fd23ef0aadce588131cf04f92f8466327f46b3fc614fbe012e1a341af23f)
BibTeX
@misc{dc9ac97f9fbeee,
title = {Whose turn is it? Context-guided model routing for stateful agents — arXiv:2610.19292},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19292},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ac97f9fbeee; sha256 b6c2fd23ef0aadce588131cf04f92f8466327f46b3fc614fbe012e1a341af23f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19292. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Model routing can reduce the cost of LLM applications by assigning simpler requests to cheaper models without sacrificing the quality of the response. However, most routers treat requests as independent. Stateful agents do not operate under this assumption: a user turn may require multiple model and tool calls, its difficulty depends on the state produced by earlier turns, and changing models can sacrifice reuse of the conversational prompt cache. We study zero-shot, cost-aware routing at the user-turn boundary, systematically varying the routing rule, access to session history, candidate models that differ in size, reasoning effort, or model provider, and prompt-cache behavior. We evaluate on multi-turn versions of SheetCopilot and SpreadsheetBench 2, where persistent workbooks and cross-turn dependencies make isolated routing decisions especially brittle. At a matched offloading rate, giving the router session history improves task pass rate over the same router without history, with gains for every model pair; history-aware routing remains within one point of always using the expensive model. We also found that cost depends on execution dynamics rather than token prices alone: the cheaper model's per-task cost advantage narrows from 6.8x to 3.2x on longer sessions. A closed form cache analysis further shows that downward switches (expensive to cheap) recover their cache cost within two LLM calls, whereas upward switches do not break even under the evaluated conditions. Together, these results show that agent routing is a sequential decision problem: effective policies must account for what happened earlier in the session and for the asymmetric cost of switching models. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.19292 — 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 2026-10-15T19:35:48.210Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).