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.
L-autoda: Leveraging large language models for automated decision-based adversarial attacks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.