AdaE-SAEA uses meta-RL to adaptively select infill criteria and ensemble surrogate strategies (bagging/boosting) that balance robustness and accuracy across search phases in SAEAs.
As-llm: When algorithm se- lection meets large language model
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.NE 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
R2SAEA fine-tunes an LLM with RL to reason about solution relations for surrogate-assisted evolutionary optimization, reporting improved relation prediction and SOTA performance on single- and multi-objective benchmarks.
citing papers explorer
-
Meta-Black-Box Optimization with Ensemble Surrogate Modeling for Robustness-Accuracy Trade-off within SAEA
AdaE-SAEA uses meta-RL to adaptively select infill criteria and ensemble surrogate strategies (bagging/boosting) that balance robustness and accuracy across search phases in SAEAs.
-
Relation Reasoning with LLMs in Expensive Optimization
R2SAEA fine-tunes an LLM with RL to reason about solution relations for surrogate-assisted evolutionary optimization, reporting improved relation prediction and SOTA performance on single- and multi-objective benchmarks.