SHA-PF uses initial simulation data to select a 'hard but promising' anchor satisfaction state and evolves LLM-generated formulations that prioritize it, reaching target designs with fewer expensive simulations on antenna and hydrology benchmarks.
Title resolution pending
1 Pith paper cite this work, alongside 542 external citations. Polarity classification is still indexing.
1
Pith paper citing it
542
external citations · OpenAlex
fields
cs.NE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Search Hardness-Aware LLM-Based Problem Formulation for Expensive Simulation-Driven Design
SHA-PF uses initial simulation data to select a 'hard but promising' anchor satisfaction state and evolves LLM-generated formulations that prioritize it, reaching target designs with fewer expensive simulations on antenna and hydrology benchmarks.