arXiv：cs.AI· Zehuan Chen, Chunhe Song·· 3 小时前
ORDO：面向 MIP 预求解的操作级轮次感知动态排序
ORDO: Operation-level Round-aware Dynamic Ordering for MIP Presolve
AI 导读
ORDO 将 MIP 预求解规划重构为统一原子动作空间上的自回归序列生成，让决策对象从参数配置转向动作序列。在多个未见领域上，该框架实现端到端零样本加速，据作者称这是预求解动作序列上的首次；加速幅度随领域而异，最强领域在加入 sequence racing 后提升最大。部署时通过修改 SCIP 源码注入序列并记录实际执行的动作与轮次，候选序列并发运行并保留胜者。
正文
Abstract:Presolve strongly affects mixed-integer programming (MIP) performance, yet learning-based methods only optimize parameter configurations and cannot express the non-commutative temporal dependencies among actions, whose default order is nearly unique on most domains, yet functionally necessary: artificially shuffling the order of the same sequence inflates the tail of the solve-time distribution by up to several-fold. We recast presolve planning as autoregressive sequence generation over a unified atomic action space, moving the decision object to action sequences; we call this framework ORDO---Operation-level Round-aware Dynamic Ordering for MIP Presolve. Its payoff is cross-domain generalization: on multiple unseen domains it attains end-to-end zero-shot speedup---to our knowledge the first for presolve action sequences---varying by domain and not explained by corpus richness, the strongest domain reaching the largest speedup once racing is added. Deployment uses sequence racing, in which candidate sequences run concurrently and the winner is kept, enabled by an execution-and-observation facility, added by modifying the SCIP source, that injects sequences along the native path and records which actions actually execute and in which round.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11294 [cs.AI] |
| (or arXiv:2610.11294v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11294 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zehuan Chen [view email]
[v1]
Thu, 8 Oct 2026 05:59:52 UTC (819 KB)
来源：arXiv：cs.AI · arxiv.org