跳到正文
arXiv cs.AI· Andre Albrecht, Enzo Morosini Frazzon, Leandro C. Coelho, Bruno Vieira·· 4 小时前精选AI 评分66

研究比较智能体编写启发式与商业求解器在未解 job-shop 基准上的表现

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

AI 导读

论文研究前沿大语言模型作为编码智能体(仅用开源工具)能否在质量和速度上匹敌商业求解器,所有运行均被记录并由独立校验器核验。

推荐理由

论文用公开运行记录和独立校验器对比大语言模型编码智能体与商业求解器在未解排程基准上的表现,结果可复核。

正文 · 原文

View PDF HTML (experimental)

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.
Comments: 27 pages, 4 figures, 14 tables. Submitted to International Transactions in Operational Research. Data, schedules, checkers and code: this https URL
Subjects: Optimization and Control (math.OC); Artificial Intelligence (cs.AI)
MSC classes: 90B35
Cite as: arXiv:2611.17682 [math.OC]
  (or arXiv:2611.17682v1 [math.OC] for this version)
  https://doi.org/10.48550/arXiv.2611.17682

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Leandro Coelho [view email]
[v1] Fri, 13 Nov 2026 02:50:02 UTC (79 KB)

来源:arXiv cs.AI · arxiv.org