Pith. sign in

REVIEW 13 cited by

OptiMUS: Optimization Modeling Using MIP Solvers and large language models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.06116 v2 pith:SWL7TDZ5 submitted 2023-10-09 cs.AI

OptiMUS: Optimization Modeling Using MIP Solvers and large language models

classification cs.AI
keywords optimusproblemslanguageoptimizationagentcodedatasetdeveloping
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Optimization problems are pervasive across various sectors, from manufacturing and distribution to healthcare. However, most such problems are still solved heuristically by hand rather than optimally by state-of-the-art solvers, as the expertise required to formulate and solve these problems limits the widespread adoption of optimization tools and techniques. We introduce OptiMUS, a Large Language Model (LLM)-based agent designed to formulate and solve MILP problems from their natural language descriptions. OptiMUS is capable of developing mathematical models, writing and debugging solver code, developing tests, and checking the validity of generated solutions. To benchmark our agent, we present NLP4LP, a novel dataset of linear programming (LP) and mixed integer linear programming (MILP) problems. Our experiments demonstrate that OptiMUS solves nearly twice as many problems as a basic LLM prompting strategy. OptiMUS code and NLP4LP dataset are available at \href{https://github.com/teshnizi/OptiMUS}{https://github.com/teshnizi/OptiMUS}

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction

    cs.AI 2026-07 conditional novelty 7.0

    A²utoLPBench is a generator that produces unlimited LP word problems with ground-truth answers known by construction via inverse-KKT, bundled with a Docker environment for agent evaluation.

  2. Agentic MIP Research: Accelerated Constraint Handler Generation

    cs.AI 2026-05 unverdicted novelty 7.0

    LLM agents in a solver-aware harness recover global constraints from MIP formulations, generate executable propagation-only handlers for SCIP, and solve five additional MIPLIB 2017 instances.

  3. ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization Modeling

    cs.AI 2026-05 unverdicted novelty 7.0

    ORPilot is the first agentic LLM system built specifically for production optimization modeling, using interview, data collection, parameter computation agents and a solver-agnostic intermediate representation to hand...

  4. Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization

    cs.AI 2026-04 conditional novelty 7.0

    DeInfer reduces parallel inference communication cost for decomposed LLMs by up to 78% by moving collective operations into the low-rank latent space and redesigning KV-cache reconstruction for static graph compatibility.

  5. ModelLens: Finding the Best for Your Task from Myriads of Models

    cs.LG 2026-05 unverdicted novelty 6.0

    ModelLens learns a performance-aware latent space from 1.62M leaderboard records to rank unseen models on unseen datasets without forward passes on the target.

  6. Relation Reasoning with LLMs in Expensive Optimization

    cs.NE 2026-04 unverdicted novelty 6.0

    R2SAEA fine-tunes an LLM with RL to reason about solution relations for surrogate-assisted evolutionary optimization, reporting improved relation prediction and SOTA performance on single- and multi-objective benchmarks.

  7. Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization

    cs.AI 2026-04 unverdicted novelty 6.0

    EvoOR-Agent co-evolves agent architectures as AOE-style networks with graph-mediated recombination and knowledge-base-assisted mutation to outperform fixed LLM pipelines on OR benchmarks.

  8. AutoOR: Scalably Post-training LLMs to Autoformalize Operations Research Problems

    cs.LG 2026-04 unverdicted novelty 6.0

    AutoOR uses synthetic data generation and RL post-training with solver feedback to enable 8B LLMs to autoformalize linear, mixed-integer, and non-linear OR problems, matching larger models on benchmarks.

  9. LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection

    cs.CL 2025-10 unverdicted novelty 6.0

    LISTEN is an agentic LLM framework for multi-objective selection using natural language, with LISTEN-U refining a parametric utility function and LISTEN-T performing tournament-style batch selections, showing context-...

  10. LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection

    cs.CL 2025-10 conditional novelty 6.0

    LISTEN uses LLMs as zero-shot preference oracles, via iterative utility refinement (LISTEN-U) or tournament comparisons (LISTEN-T), to select preferred items from large multi-objective candidate sets.

  11. Optimization and Constraint Modeling using LLMs with a Retrieval Augmented Generation Process

    cs.AI 2026-06 reject novelty 5.0

    A RAG pipeline with 500 synthetic problem-solution pairs is claimed to improve LLM optimization modeling accuracy, but the evaluation compares different error tolerances between conditions.

  12. Vehicle Routing Problem Meets Large Language Models: An Overview and Perspectives

    math.OC 2026-07 unverdicted novelty 4.0

    Survey organizing LLM uses for VRP into modeler, designer, and coordinator roles, covering variants, solvers, benchmarks, and two experiments.

  13. Learning to Optimize by Differentiable Programming

    cs.MS 2026-01 unverdicted novelty 2.0

    A tutorial survey of differentiable-programming-based first-order optimization, with dual-based PyTorch case studies and no new results.