Neural Bandit Based Optimal LLM Selection for a Pipeline of Subtasks

ArXi:2508.09958v3 Announce Type: replace-cross As large language models (LLMs) become increasingly popular, there is a growing need to predict which out of a set of LLMs will yield a successful answer to a given query at low cost. This problem promises to become even relevant as LLM agents are asked to solve an increasing variety of "agentic'' AI tasks. Such tasks are often broken into smaller subtasks, each of which can then be executed by a LLM expected to perform well on that specific subtask.