FrugalEvo introduces a cost‑aware evolutionary framework that pairs a high‑cost, powerful LLM with a cheaper LLM to explore and refine program solutions, respectively. It incorporates a cache‑efficient evolution process that maximizes prefix reuse across steps and defines a Budget‑Aware Area Under the Curve (BA‑AUC) metric to evaluate solution quality within a fixed cost budget. Across ten mathematical and systems optimization tasks, FrugalEvo matches or surpasses state‑of‑the‑art baselines in final solution quality and achieves higher BA‑AUC on nine tasks, while delivering new state‑of‑the‑art performance on circle packing for costs as low as $0.55 to $1.68.
By Hui Chen, Xuan Qi, James Xu Zhao, Zhaopeng Feng, Shilong Liu, Kuang Xu, Pang Wei Koh, Bryan Hooi
arXiv:2606. 26164v1 Announce Type: new Abstract: Finding all modes of a multimodal black-box function is a fundamental challenge in optimization, Bayesian inference, and scientific computing.
By Ira Wolfson
arXiv:2606. 11015v1 Announce Type: new Abstract: Tuning controllers for strongly coupled multi-input multi-output (MIMO) industrial processes is hard: decentralized classical auto-tuning ignores loop interaction, and local numerical optimization from natural initializations stalls in the resulting non-convex cost landscape.
By Jiaxuan Chen, Haonan Li, Yang Shu
arXiv:2607. 17398v1 Announce Type: cross Abstract: Analytical placers rely on differentiable objective functions to guide placement, typically combining intermediate surrogate metrics such as half-perimeter wirelength (HPWL) and cell-density penalties.
By Ruogu Chen, Weihua Xiao, Ramesh Karri, Jie Han
Finding all modes of a multimodal black-box function is a fundamental challenge in optimization, Bayesian inference, and scientific computing. Existing approaches -- basin-hopping, CMA-ES, multistart gradient descent -- operate sequentially and cannot exploit the massive parallelism of modern GPU hardware.
arXiv:2606. 21641v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "warm-start" search from prior knowledge, proposing strong configurations in very few evaluations.
By Carson Rodrigues, Oysturn Vas, Isaiah Abner DCosta, Nithish Kumar Prabhakaran
Large traveling salesman problem (TSP) instances require a solver to allocate limited computation while preserving the validity of its outputs. Existing neural--operations-research (OR) hybrids predict guidance without requiring learned transitions to satisfy constraints discovered during search.
arXiv:2610. 21001v1 Announce Type: new Abstract: Column generation folklore warns that initial columns hurt: a warm start may bias the dual and slow the root of branch-price-and-cut.
By Haoran Liu, Yu Yang
arXiv:2609.26077v1 Announce Type: new
Abstract: A Strassen-type algorithm has many realizations with the same exact product and multiplication count yet different fp8 error because basis changes resh...
By Shuxiao Xie, Shuyang Xie, Yuan Cao, Dezhi Ran, Wei Yang, Tao Xie
The paper introduces FARO, a function‑space adaptive optimizer that treats each parameter block as a decision unit, assigning geometry based on counterfactual return and reallocating budgets via cross‑block equal risk contribution (ERC). On a GPT‑style model trained on FineWeb, FARO‑Adaptive matches the best hand‑designed optimizer (NorMuonAndAdam) while FARO‑ERC further reduces clean‑data loss by an average of 0.0136 nats across six seeds, achieving a robust improvement without extra time or memory. The method works by trimming the riskiest blocks and remains effective even under corrupted data streams.
By Xiaojun Wu, Cehao Yang, Xuhui Jiang, Chengjin Xu, Jia Li, Jian Guo
arXiv:2606. 05186v1 Announce Type: new Abstract: Budget-constrained micro-pretraining often requires triaging many candidate recipes on a shared accelerator before larger search budgets are spent.
By Felipe Chavarro Polania
The paper introduces AgenticBBO-Bench, a cross‑domain benchmark for evaluating large language model agents on black‑box optimization tasks such as synthetic functions, hyperparameter tuning, database tuning, chip design, and molecular design. Experiments show that agentic BBO outperforms direct LLM‑based methods in all five domains and beats the best numerical optimizers in four. The study also analyzes the impact of optimization tools, task semantics, prior knowledge, and the LLM’s role, finding that numerical tools are not consistently helpful, task semantics are broadly useful, and numerical optimizers can capitalize on agent‑generated search trajectories.
By Ming Chen, Rong-Xi Tan, Ke Xue, Yu-Jie Zhou, Taiye Lu, Zhi-Xuan Gao, Peng Xie, Zijun Shen, Chen Lu, Haopu Shang, Chao Qian