Problem
Classical optimization problems carry hard feasibility constraints that vanilla language models often violate.
Project
LLMs for Optimization Problems
Research-driven project exploring LLM + graph representations for constrained optimization (JSSP and related tasks).
Approach
I modeled JSSP instances as disjunctive graphs, serialized precedence and machine conflicts explicitly, and paired that representation with LoRA fine-tuning.
Result
The pipeline produced a much more structured optimization workflow and made training/runtime tradeoffs manageable for course-scale experimentation.
What I built
I treated scheduling as a structure-first problem instead of a pure prompting problem. The project converts job shop instances into graph-shaped representations so the model sees precedence and machine conflicts explicitly.
Core decisions
- Serialized machine and operation constraints instead of relying on free-form descriptions.
- Used disjunctive graphs to preserve conflict structure.
- Applied 4-bit LoRA fine-tuning to keep experimentation feasible.
- Focused on failure slices where outputs looked plausible but violated constraints.
What mattered most
The project became stronger once I stopped asking whether the LLM could "solve optimization" in the abstract and started asking whether the representation exposed enough constraint information for the model to reason over.