REP-HO：用 LLM 替代启发式规则规划异构优化的评估分配
LLM-Based Evaluation Planning for Heterogeneous Optimization
这篇论文把 LLM 塞进优化器里当决策规划器，替代人工设计的启发式规则，用 DeepSeek 做的版本在 5 种场景里都进前二，思路挺有意思。
论文提出 REP-HO，用 LLM 替代 MFE-NSGA-III 中基于人工设计指标的选择步骤，输入替代模型预测、不确定性、评估成本和预算状态等优化状态信息。
在覆盖成本失衡、约束难度、替代模型保真度、预算水平、目标冲突的 5 种异构场景中，两个变体之一均取得最佳平均排名。REP-HO(DeepSeek) 在所有场景中保持第一或第二名，加入自适应最近邻摘要后结果更稳定。
规划器表现出自适应分配行为，如在预算紧张时优先评估约束、在替代模型可靠性变化时重新分配约束评估预算。
LLM-Based Evaluation Planning for Heterogeneous Optimization
Heterogeneous optimization problems require an optimizer to decide not only which candidate solutions to evaluate, but also which objectives and constraints should be evaluated under different costs and fidelities. Existing SOTA methods such as MFE-NSGA-III address this setting with manually designed selection metrics, but their behavior is largely determined by predefined heuristic rules and hyperparameters. In this work, we propose REP-HO, a reasoning-based evaluation planner that replaces the rule-based mixed-fidelity selection step with a large language model (LLM) planner. The LLM receives the same primitive optimization-state information as the heuristic planner, such as surrogate predictions, uncertainties, evaluation costs, and budget status. We first show that REP-HO achieves competitive performance compared to the human-designed metric-based method (MFE-NSGA-III). We then further enhance each decision with an adaptive nearest-neighbor summary, leading to better and more stable results. We evaluate REP-HO across five heterogeneous regimes covering cost imbalance, constraint difficulty, surrogate fidelity, budget level, and objective conflict. Across these regimes, one of the two variants obtains the best mean ranking score in every regime, REP-HO(Deepseek) is first or second throughout, and the planner shows adaptive allocation behavior, such as prioritizing constraint evaluations under tighter budgets and reallocating constraint evaluation budget when surrogate reliability changes. These results suggest that LLMs can serve as flexible evaluation planners for heterogeneous optimization, offering a general alternative to fixed hand-designed metrics.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include REP-HO, DeepSeek, LLM, 优化算法.
Primary source verification: published directly by arXiv: DeepSeek with first-party authority.