AI Paper Atlas

Research map / Bandits and online learning / Multi-armed bandits

Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm That Provably Exploits Model Similarity

Zifan Lyu, Chahine Nejma, Tobias Wegel, Fanny Yang, Florian E. Dorner

ICML 2026 · Bandits and online learning › Multi-armed bandits · approach: Fixed-confidence versus fixed-budget identification · 0 citations (OpenAlex)

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
add synchronization (same queries for all models) to Successive Rejects (ablation)Successive Rejects · 15 benchmarks avg, 12% budgetidentification accuracy (%): 89.7 -> 95.1Improved
add synchronization to Successive Rejects (ablation)Successive Rejects · 15 benchmarks, 100% confidence budget (max)confidence budget (%): 43 -> 35Improved
add synchronization to uniform sampling (ablation)Uniform Sampling · 15 benchmarks avg, 12% budgetidentification accuracy (%): 36.7 -> 46.8Improved
add synchronization to UCB-E (a=1.0) (ablation)UCB-E · 15 benchmarks avg, 12% budgetidentification accuracy (%): 86.8 -> 89.4Improved
add synchronization to UCB-E (a=0.1) (ablation)UCB-E · 15 benchmarks avg, 12% budgetidentification accuracy (%): 66.9 -> 74.0Improved
add synchronization to UCB-E (a=10.0) (ablation)UCB-E · 15 benchmarks avg, 12% budgetidentification accuracy (%): 63.3 -> 73.3Improved
add synchronization to uniform sampling (ablation)Uniform Sampling · 15 benchmarks, 90% confidence budget (mean)confidence budget (%): 73 -> 59Improved
add synchronization to Successive Rejects (ablation)Successive Rejects · 15 benchmarks, 90% confidence budget (mean)confidence budget (%): 11 -> 8Improved
lower UCB-E exploration parameter a from 10.0 to 1.0UCB-E · 15 benchmarks, 90% confidence budget (mean)confidence budget (%): 19 -> 10Improved
raise UCB-E exploration parameter a from 1.0 to 10.0UCB-E · 15 benchmarks, 100% confidence budget (mean)confidence budget (%): 68 -> 22Improved
remove the 5% warm-up from UCB-E-LRF (ablation)UCB-E-LRF · 15 benchmarks avg, 12% budgetidentification accuracy (%): 60.8 -> 46.7Hurt

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