AI Paper Atlas

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

Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery

Xinzhe Yuan, Zhuo Chen, Jianshu Zhang, Huan Xiong, Nanyang Ye, Yuqiang Li, Qinying Gu

ICLR 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery · 1 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
continuous LLM region-lifted preference vs standard BOLGBO · LNP3, HPLC, Cross-barrel, Concrete (dry)best objective / convergenceImproved
LGBO vs GPBO and LLAMBOLGBO · Fe-Cr wet labiterations to 90% of best: more than 10 -> 6Improved
replace LLM suggestions with random lifted regions (ablation)LGBO · HPLCconvergence speedHurt
use larger or science-pretrained LLM backbone (ablation)LGBO · HPLCstabilityImproved
use Thinking LLM variant instead of Instruct (ablation)LGBO · HPLCfinal value vs convergence speedMixed
share LLM-suggested initialization (LLAMBO vs LGBO)LLAMBO · LNP3convergenceNo clear effect
LGBO vs GPBO on low-dimensional Cross-barrelLGBO · Cross-barreltoughnessImproved

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