93% of GPT-4 performance at 1/4 cost: LLM routing with weak bandit feedback
Computer Science > Machine Learning arXiv:2508.21141 (cs) [Submitted on 28 Aug 2025] Title:Adaptive LLM Routing under Budget Constraints Authors:Pranoy Panda, Raghav Magazine, Chaitanya Devaguptapu, Sho Takemori, Vishal Sharma View a PDF of the paper titled Adaptive LLM Routing under Budget Constraints, by Pranoy Panda and 4 other authors View PDF HTML (experimental) Abstract:Large Language Models (LLMs) have revolutionized natural language processing, but their varying capabilities and costs pose challenges in practical applications. LLM routing addresses this by dynamically selecting the most suitable LLM for each query/task. Previous approaches treat this as a supervised learning problem, assuming complete knowledge of optimal query-LLM pairings. However, real-world…
