An LLM-based evolutionary search discovers novel kernels for high-dimensional Bayesian optimization, achieving an average rank of 1.2 out of 17 on five benchmarks via two-stage proposal and LOO-CRPS selection.
Mathematical discoveries from program search with large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
An LLM agent can improve itself at test time by rewriting its surrounding executable harness from unlabeled traces, using only proxy signals and a frozen model.
citing papers explorer
-
Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization
An LLM-based evolutionary search discovers novel kernels for high-dimensional Bayesian optimization, achieving an average rank of 1.2 out of 17 on five benchmarks via two-stage proposal and LOO-CRPS selection.
-
TTHE: Test-Time Harness Evolution
An LLM agent can improve itself at test time by rewriting its surrounding executable harness from unlabeled traces, using only proxy signals and a frozen model.