AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

Scaling Multi-Task Bayesian Optimization with Large Language Models

Yimeng Zeng, Natalie Maus, Haydn Thomas Jones, Jeffrey Tao, Fangping Wan, Marcelo Der Torossian Torres, Cesar de la Fuente-Nunez, Ryan Marcus, Osbert Bastani, Jacob R. Gardner

ICLR 2026 · Probabilistic and scientific modeling › Bayesian optimization · approach: Local and high-dimensional Bayesian optimization

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
fine-tune LLM on more BO trajectories (1426 vs 1138 tasks) (ablation)BOLT · Query plan optimization, Best@50summed runtime: 78.16 -> 63.68Improved
fine-tune on 1426 tasks versus 1138 tasks, one-shot (ablation)BOLT · Query plan optimization, Best@1summed runtime: 202.04 -> 160.22Improved
replace old solutions with newer better ones (same training size) versus keeping old data (ablation)BOLT-1138 · Query plan optimization, Best@50summed runtime: 78.16 -> 64.03Improved
add more data on top of replaced better data (BOLT-1426 vs BOLT-1138*) (ablation)BOLT · Query plan optimization, Best@50summed runtime: 64.03 -> 63.68Improved
add self-augmentation (fine-tune on own best generations) without extra BO runs (ablation)BOLT-1138 and BOLT-1426 · Query plan optimizationsummed runtime on 100 validation queries: about 62 seconds for both self-augmented modelsImproved
use greedy decoding (temperature 0) instead of 0.7 (ablation)BOLT · Query plan optimization, one-shotone-shot performanceImproved
fine-tune open-source Qwen-2.5-7B instead of GPT-4o-mini on BOLT-1426 data (ablation)BOLT · Query plan optimization, Best@50summed runtime: 61.54 -> 62.04No clear effect
fine-tune open-source Llama-3.1-8B instead of GPT-4o-mini (ablation)BOLT · Query plan optimization, Best@50summed runtime: 61.54 -> 155.55Hurt
initialize BO with best solutions of previously solved tasks instead of BOLT samples (ablation)BOLT-1426 · Query plan optimization, first 10 validation taskssummed runtime: 7.21 -> 9.18Hurt
run full BO after BOLT-1426 initialization (ablation)BOLT-1426 · Query plan optimization, first 10 validation taskssummed runtime: 7.21 -> 6.43Improved
scale BOLT training tasks beyond about 20 versus multi-task GP (DKT/FSBO)BOLT vs DKT/FSBO · Query plan optimization BO curvesBO performanceImproved
more experts in POGPE/SGPE ensemblesPOGPE/SGPE · Query plan and peptide designBO performanceMixed

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