AI Paper Atlas

Research map / Large language models / Agents, code and math

LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation

Zhuo Chen, Xinzhe Yuan, Jianshu Zhang, Jinzong Dong, Ruichen Zhou, Yingchun Niu, Tianhang Zhou, Yu Yang Fredrik Liu, Yuqiang Li, Nanyang Ye, Qinying Gu

ICML 2026 · Large language models › Agents, code and math · approach: LLMs for optimization and heuristics · 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
use LABO (LLM-fidelity KOH surrogate with gating) instead of vanilla BO, LLAMBO, BOPRO, CAKEBayesian optimization · six scientific formula tasksbest objective under fixed real budgetImproved
give vanilla BO the same LLM-suggested initial candidates as LABO (ablation)Vanilla BO · COF (14D)best objectiveImproved
use informative LLM-fidelity predictions instead of random values in the same range (ablation)LABO · COF (14D)convergence and final objectiveImproved
use larger or reasoning-enhanced LLM backbone (ablation)LABO · COF (14D)final objectiveImproved
raise gating threshold tau from 0.60 to 0.75 (ablation)LABO · COF (14D)final objective: 10.778 -> 11.228Improved
raise gating threshold tau from 0.75 to 0.85 (ablation)LABO · COF (14D)final objective: 11.228 -> 11.171Hurt
raise gating threshold tau from 0.75 to 0.85 (ablation)LABO · Fullerene (3D)final objective: 0.9512 -> 0.9499Hurt
raise gating threshold tau from 0.60 to 0.85 (ablation)LABO · COF (14D)iterations to 90% of best: 24.60 -> 12.60Improved
raise gating threshold tau from 0.60 to 0.85 (ablation)LABO · Fullerene (3D)LLM- to real-fidelity query ratio: 1.54 -> 14.60Mixed

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