LDST：用 LLM 读求解器日志来调优混合整数规划参数
Log-Driven Semantic Tuning for Mixed Integer Programming Solvers
一篇用 LLM 替代黑盒调参的论文：直接读 MIP 求解器日志找瓶颈再改配置，10 次提案就打得过 SMAC3 跑 50 次，做运筹优化的可以看看。
arXiv 论文提出 Log-Driven Semantic Tuning（LDST），用 LLM 替代黑盒优化来配置 MIP 求解器。LDST 从求解器日志中提取诊断信息，让 LLM 基于参数含义提出稀疏的配置修改，并在执行前验证每个提案。方法还引入基于日志的完成时间估计，把已解和未解的运行放在同一时间尺度上比较。在来自 5 个基准集的 215 个实例上，LDST 相比 SMAC3、RBFOpt 和随机搜索中的最优者，将易实例的几何平均损失降低 43.9%，中等实例降低 16.7%；LDST 用 10 个提案取得的损失低于这些基线用 50 个提案的结果。
Log-Driven Semantic Tuning for Mixed Integer Programming Solvers
Automated configuration of mixed-integer programming (MIP) solvers largely relies on black-box optimization. Each trial requires an expensive solver run and provides only a scalar outcome, so tuning can require many such evaluations. Human experts take a different approach. They inspect solver logs, identify performance bottlenecks, and adjust the parameters that address them. We propose Log-Driven Semantic Tuning (LDST), which uses a large language model (LLM) to automate this process. LDST extracts compact diagnostics from solver logs, uses the LLM to propose sparse edits to the current best configuration based on parameter meanings and observed solver behavior, and validates each proposal before execution. A regime-adaptive objective selects the tuning signal according to the information available from a time-limited run, while a log-based completion signal estimates completion time from branch-and-bound tree growth recorded in ordinary solver logs, so that solved and unsolved runs share one time scale. On 215 instances from five benchmark sets, LDST reduces geometric-mean loss by 43.9% on easy instances and 16.7% on intermediate instances relative to the best of SMAC3, RBFOpt, and random search. In both regimes, LDST achieves a lower loss with 10 proposals than any of these baselines achieves with 50. Configurations that LDST tunes on a single instance also transfer better than baseline configurations to unseen instances of the same family.