math.OCNov 13, 2026

Agent-written heuristics versus commercial solvers on unsolved job-shop benchmark instances

Authors: Andre Albrecht, Enzo Morosini Frazzon, Leandro C. Coelho, Bruno Vieira

Organizations: ProLogIS – Production and Logistics Intelligent Systems, Department of Production Engineering, Federal University of Santa Catarina (UFSC), Florianópolis, SC, 88040-900, Brazil · CIRRELT and Canada Research Chair in Integrated Logistics, Université Laval, Québec, QC, G1V 0A6, Canada · Department of Industrial Engineering, Federal Institute of Santa Catarina (IFSC), Caçador, SC, 89503-550, Brazil

Abstract

Commercial solvers are the standard tool for difficult scheduling problems. We study whether a frontier large language model, used as a coding agent with open-source tools only, can match them in quality and speed. We report every run, and independent checkers verify every schedule. On the 100,000-operation job shop tai_100_1000_1, an agent-written solver reached 525,515, below OptalCP, Hexaly, and CP Optimizer. Unchanged, it improved all ten instances of the family and closed two. With equal budgets on the same workstation, it ended 0.0-1.8% above the lower bound, against 2.6-5.8% for CP Optimizer and 2.4-4.4% for Hexaly. On the Behnke-Geiger flexible job shops, an agent-written tabu search improved 11 of 32 open instances. With two transport robots, an agent-written solver improved seven of ten MKT instances. New lower bounds show that four published MKT values cannot be attained on the distributed instance files. Agent-run improvement campaigns closed eight further instances.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Agentic AI-Assisted Modeling for Production Scheduling: Assessment in Constraint Programming

    Oct 7, 2026Ángel Sánchez-Fernández, Javier Pernas-Álvarez, Diego Crespo-PereiraNatural Language to Optimization ModelingCombinatorial Optimization

  2. ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?

    Jun 18, 2026Jiajun Li, Mingshu Cai, Yixuan Li +5LLM Agent EvaluationAI Agent Benchmarks

  3. Distribution-Aware Programming: Learning Specialized Solvers from Experience

    May 13, 2026Saharsh Koganti, Priyadarsi Mishra, Pierfrancesco Beneventano +1Large Language Model-Guided OptimizationLLM-Based Program Synthesis