Metraipolis › archive › dc_c52152c35360
Error-Aware Reverse Auction Mechanism for Large Language Model Routing — arXiv:2608.12719
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12719
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:18:05.396Z
- SHA-256 of the archived text
8cbdc07ec0213d7eeb75aeef06c315f7b5ea78df162600c936fefc30e90baaac- Stable URL of this page
https://metraipolis.com/documento/dc_c52152c35360
How to cite
Error-Aware Reverse Auction Mechanism for Large Language Model Routing — arXiv:2608.12719 — arXiv (en), https://arxiv.org/abs/2608.12719 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c52152c35360 (Metraipolis archive dc_c52152c35360, sha256 8cbdc07ec0213d7eeb75aeef06c315f7b5ea78df162600c936fefc30e90baaac)
BibTeX
@misc{dcc52152c35360,
title = {Error-Aware Reverse Auction Mechanism for Large Language Model Routing — arXiv:2608.12719},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12719},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c52152c35360; sha256 8cbdc07ec0213d7eeb75aeef06c315f7b5ea78df162600c936fefc30e90baaac},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12719. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Routing each query to a cost-effective large language model (LLM) is critical for balancing quality and cost, yet most routers rely on a centralized task center to predict model performance, creating an information-risk mismatch and a scalability bottleneck as the model pool grows. We formulate LLM routing as a market-based allocation problem among strategic providers and propose a routing paradigm that shifts ex-ante prediction to LLM providers via a reverse auction, where providers submit self-predicted acceptance probabilities and execution costs. To account for noisy provider predictions and center evaluations, we introduce the \textit{\textbf{E}rror-\textbf{A}ware \textbf{R}everse \textbf{A}uction \textbf{M}echanism} (EA-RAM), which explicitly models this Dual Error. We prove that, under a private-evaluation-belief structure, truthful effective-surplus reporting is incentive compatible in the reduced-form score space and individually rational under sellers' subjective beliefs, establish sufficient conditions for center rationality, and derive an explicit social-welfare loss bound. We further identify robustness effects: opposite-signed errors can cancel, vanishing-tail link functions (e.g., logistic) stabilize clear-cut cases via saturation, and extra noise smooths belief maps and reduces their maximal local sensitivity. Simulations and real-world benchmarks show that EA-RAM is robust to Dual Error and achieves a better cost--performance Pareto frontier than centralized baselines, with additional gains from provider-side local information, validating its practical effectiveness.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Computer Science and Game Theory (cs.GT) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.12719 — 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 2026-10-19T04:13:06.695Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).