Guanhua Zhang, Moritz Hardt · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31428 · open-access PDF
Model bahasa besar (LLM) berbeda dalam kemampuan dan biaya, memotivasi metode routing yang secara adaptif memilih model untuk setiap kueri. Metode ini bergantung pada prediksi kinerja: diberikan kueri, estimasi apakah sebuah model akan menjawabnya dengan benar. Kebanyakan metode routing melatih prediksi terpisah dari kinerja model kandidat untuk membimbing pemilihan model. Pekerjaan kami menunjukkan bahwa prediksi kinerja hanya mengalahkan garis dasar sederhana ketika model kandidat suboptimal pada tugas atau prediktor kinerja menambahkan kapasitas yang signifikan dibandingkan dengan model kandidat.
Machine translation (Meta M2M100); the English original follows.
Large language models (LLMs) differ in capabilities and costs, motivating routing methods that adaptively choose a model for each query. These methods rely on performance prediction: given a query, estimate whether a model will answer it correctly. Most routing methods train separate predictors of candidate models' performance to guide model selection. Our work shows that performance prediction only beats a simple baseline when the candidate model is suboptimal on the task or the performance predictor adds significant capacity relative to the candidate model. Specifically, we take a model's se
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31428, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange