MétaCan
Menu
Back to cohort

LLMs for Bayesian Optimization in Scientific Domains: Are We There Yet?

2025· article· W4416034102 on OpenAlexfundno aff
Jason Hartford, Bang Liu

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicAdvanced Multi-Objective Optimization Algorithms
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of CanadaCanadian Institute for Advanced Research
KeywordsBayesian probabilityKey (lock)Bayesian inferenceBayesian optimization

Abstract

fetched live from OpenAlex

Large language models (LLMs) have recently been proposed as general-purpose agents for experimental design, with claims that they can perform in-context experimental design.We evaluate this hypothesis using both open-and closed-source instruction-tuned LLMs applied to genetic perturbation and molecular property discovery tasks.We find that LLM-based agents show no sensitivity to experimental feedback: replacing true outcomes with randomly permuted labels has no impact on performance.Across benchmarks, classical methods such as linear bandits and Gaussian process optimization consistently outperform LLM agents.We further propose a simple hybrid method, LLM-guided Nearest Neighbour (LLMNN) sampling, that combines LLM prior knowledge with nearest-neighbor sampling to guide the design of experiments.LLMNN achieves competitive or superior performance across domains without requiring significant in-context adaptation.These results suggest that current openand closed-source LLMs do not perform incontext experimental design in practice and highlight the need for hybrid frameworks that decouple prior-based reasoning from batch acquisition with updated posteriors.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.009
metaresearch head score (Gemma)0.039
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.009
Threshold uncertainty score0.047

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0090.039
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0020.003
Open science0.0030.003
Research integrity0.0020.004
Insufficient payload (model declined to judge)0.0040.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.018
GPT teacher head0.293
Teacher spread0.275 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicAdvanced Multi-Objective Optimization AlgorithmsFrench-language works237,207