Stanford University
CoDICoordinated Decision
Intelligence Center

Project / Optimization

FLARE: verifying optimization models

FLARE combines language models with formal theorem proving to check whether reformulating a mixed-integer linear program preserves the underlying optimization problem. Its Lean-checked proofs support verification of proposed reformulations, evaluated using the FormulationBench benchmark.

Two models. A shared optimum.

Conceptual illustration; not a research result or system specification.

The coordination question

Does a proposed reformulation preserve the underlying optimization problem?

Explore the work

Use the public sources to explore the research, its setting, and its limitations.

FLARE paper ← All projects

Connect with CoDI

Put coordination
at the center.

Explore the research, meet our faculty, and find the right way to engage.

Explore ways to engage