arXiv:2608.23353v1 Announce Type: new Abstract: Mixed-integer programming (MIP) lies at the core of operations research and industrial optimization. While large language models (LLMs) have recently s...
arXiv:2607. 18256v1 Announce Type: new Abstract: Optimization modeling is the process of translating real-world decision problems, often described in natural language, into formal mathematical formulations and executable solver code.
arXiv:2407. 19633v4 Announce Type: replace Abstract: Optimization problems are pervasive in sectors from manufacturing and distribution to healthcare.
arXiv:2608. 07040v1 Announce Type: new Abstract: Solving combinatorial optimization problems (COPs) requires not only efficient algorithms but also carefully crafted formulations.
The paper introduces two lightweight inference harnesses, OPTICYCLE and OPTISTATE, designed to enable large language models to translate natural-language optimization problems into solver programs without additional training. Evaluated across nine benchmarks and 11 Qwen variants (0.6B–27B parameters), the harnesses consistently improve macro accuracy, with execution-guided revision boosting performance by up to 49.46 percentage points. Despite their simplicity, both harnesses outperform six adapted agentic workflows and four post-trained optimization models of comparable size, though the benefit of explicit formulation state varies by model.
arXiv:2606. 15577v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly involved in complex mathematical optimization, even if the pragmatic user who triggers them is unaware of it.
arXiv:2609.22987v1 Announce Type: new Abstract: Automated operations research (OR) modeling requires LLMs to translate natural-language decision problems into correct mathematical programs. Existing...
arXiv:2607. 18252v1 Announce Type: new Abstract: Machine learning methods have shown that data-driven policies can accelerate mixed-integer linear programming (MILP) solvers, but many such approaches remain difficult to inspect, adapt, and deploy because the learned policy is represented as an external predictor or other opaque model.
arXiv:2608. 02641v1 Announce Type: cross Abstract: Large language models (LLMs) can translate natural-language optimization problems into solver-ready formulations, but direct code generation is brittle: schema, indexing, and semantic errors can cause compilation failures, infeasible models, or incorrect objectives, while iterative repair, search, and multi-agent workflows increase inference cost.
The paper introduces Optimization Modeling from Solver Outcomes (OMSO), a reinforcement learning framework that generates solver‑specific code from natural‑language problem descriptions. OMSO uses a mathematical programming solver as a deterministic environment, executing generated code in a sandbox and converting outcomes into scalar rewards for a closed‑loop generate‑execute‑feedback‑update cycle. Experiments on datasets such as NL4OPT, MAMO, IndustryOR, and OptiBench across solvers like Gurobi, OR‑Tools, and COPT demonstrate that OMSO matches or surpasses process‑supervised fine‑tuning, enables zero‑shot transfer, and improves modeling reasoning and semantic correctness.
OptSkills is an archetype‑centric agent that learns and reasons about optimization problems using large language models. It clusters problems by underlying archetypes, explores diverse modeling and solver configurations within each cluster, and distills successful trajectories into reusable workflow‑level skills. The system achieves state‑of‑the‑art accuracy on multiple datasets, outperforming prior methods on challenging benchmarks such as MIPLIB‑NL and OOD NLCO.
Mixed-Integer Linear Programming (MILP) is a fundamental problem class in operations research and combinatorial optimization, with broad applications to industrial decision-making. Owing to their NP-hardness, however, modern solvers may struggle to find high-quality solutions for challenging MILP instances within practical time limits.