LLMs prompted with domain knowledge can generate runnable, numerically valid code for stiff and non-stiff ODEs on new diagnostic and 1000-task benchmarks.
Model reduction and neural networks for parametric pdes.The SMAI journal of computational mathematics, 7:121–157
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SciML Agents: Write the Solver, Not the Solution
LLMs prompted with domain knowledge can generate runnable, numerically valid code for stiff and non-stiff ODEs on new diagnostic and 1000-task benchmarks.