AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Near-Optimal Online Deployment and Routing for Streaming LLMs

Shaoang Li, Jian Li

ICLR 2026 · Bandits and online learning › Online convex optimization and games · approach: Online allocation with constraints

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
optimistic (UCB/LCB) stage-wise deployment plus routing LP instead of greedy or uniform baselinesStageRoute · RouterBench (36,497 queries, 11 LLMs)cumulative regretImproved
uniform random deployment instead of StageRouteuniform sampling baseline · RouterBenchbudget adherenceHurt
greedy top-M_max by UCB/LCB ratio instead of LP-based optimistic deploymentgreedy baseline · RouterBenchperformance-cost operating pointHurt
vary deployment update interval (500, 1000, 2000 rounds) (ablation)StageRoute · RouterBench, M_max=5, b=0.001cumulative regretMixed
vary concurrency cap M_max (3, 5, 10) (ablation)StageRoute · RouterBench, b=0.001cumulative regretNo clear effect
relax budget (b=0.002 vs 0.001) (ablation)StageRoute · RouterBenchcumulative regretHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy