Do Language Models Know Which Constraints Belong Together?
cs.LG, cs.AI, cs.DS, math.OC
Submitted: 2026-11-03
Updated: 2026-11-15
Code: https://github.com/junbolian/JointDW
Terminology
Sources
- OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale
- LLMs Can Design Near-Optimal OR Algorithms
- Graph Searching with Predictions
- SOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verification
- DecompGym: Benchmarking LLM Agents on Designing Decomposition Algorithms
- Learning-Augmented Query Policies
- The SCIP Optimization Suite 10.0
- FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
- LLMs for Cold-Start Cutting Plane Separator Configuration
- Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming
- Constructing Industrial-Scale Optimization Modeling Benchmark
- Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling
- ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization
- Large-Scale Optimization Model Auto-Formulation: Harnessing LLM Flexibility via Structured Workflow
- MILP-Evo: Closed-Loop Fully Automatic Design of MILP Solvers
- FLARE: Verifying MILP Reformulations with LLM-Based Theorem Proving
- Agentic MIP Research: Accelerated Constraint Handler Generation
- LLM-Guided Evolution of Symbolic Acceleration Inequality Families for MILP
- FormuEvo: LLM-Guided Evolution for Discovering Solver-Efficient Mixed-Integer Programming Formulations
- EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis