A framework of fine-tuned LLMs autoformalizes PDE control problems into signal temporal logic, generates Gurobi solver code, and proposes subgoal constraints; it beats generic LLMs in decoupled tests but shows mixed end-to-end utility gains.
Hard Figure 8: Case study of wave problems with different difficulty levels: easy (top), medium (middle), hard (bottom)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs
A framework of fine-tuned LLMs autoformalizes PDE control problems into signal temporal logic, generates Gurobi solver code, and proposes subgoal constraints; it beats generic LLMs in decoupled tests but shows mixed end-to-end utility gains.