{"work":{"id":"7498cd4e-1061-4c66-972d-258bcf0c6913","openalex_id":null,"doi":null,"arxiv_id":"2502.08773","raw_key":null,"title":"Universal Model Routing for Efficient LLM Inference","authors":null,"authors_text":"Universal Model Routing for Efficient LLM Inference , author=","year":2025,"venue":"cs.CL","abstract":"Model routing is a simple technique for reducing the inference cost of large language models (LLMs), wherein one maintains a pool of candidate LLMs, and learns to route each prompt to the smallest feasible LLM. Existing works focus on learning a router for a fixed pool of LLMs. In this paper, we consider the problem of dynamic routing, where new, previously unobserved LLMs are available at test time. We propose UniRoute, a new approach to this problem that relies on representing each LLM as a feature vector, derived based on predictions on a set of representative prompts. Based on this, we detail two effective instantiations of UniRoute, relying on cluster-based routing and a learned cluster map respectively. We show that these are estimates of a theoretically optimal routing rule, and quantify their errors via an excess risk bound. Experiments on a range of public benchmarks show the effectiveness of UniRoute in routing amongst more than 30 unseen LLMs.","external_url":"https://arxiv.org/abs/2502.08773","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-08T15:35:07.230646+00:00","pith_arxiv_id":"2502.08773","created_at":"2026-05-10T08:32:51.607956+00:00","updated_at":"2026-07-08T15:35:07.230646+00:00","title_quality_ok":true,"display_title":"Levente Kocsis and Csaba Szepesvári","render_title":"Levente Kocsis and Csaba Szepesvári"},"hub":{"state":{"work_id":"7498cd4e-1061-4c66-972d-258bcf0c6913","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":15,"external_cited_by_count":null,"distinct_field_count":6,"first_pith_cited_at":"2025-07-14T16:17:11+00:00","last_pith_cited_at":"2026-07-07T11:12:44+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-20T11:39:54.771953+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2}],"polarity_counts":[{"context_polarity":"background","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}