The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design. The long-standing endeavor of design automation has gained new momentum with the rise of large language models (LLMs).

GenMS consists of (1) a language model that takes high-level natural language as input and generates intermediate textual information about a crystal (e.g., chemical formulae), and (2) a diffusion model that takes intermediate information as input and generates

Prompt optimization aims to systematically refine prompts to enhance a language model's performance on specific tasks. Fairness detection in Terms of Service (ToS) clauses is a challenging legal NLP task that demands carefully crafted prompts to ensure reliable results. However, existing prompt optimization methods are often computationally expensive due to inefficient search strategies and costly prompt candidate scoring. In this paper, we propose a framework that combines Monte Carlo Tree Search (MCTS) with a proxy prompt evaluator to more effectively explore the prompt space while reducing evaluation costs. Experiments demonstrate that our approach achieves higher classification accuracy and efficiency than baseline methods under a constrained computation budget.

Abstract--Automatic performance tuning (auto-tuning) is widely used to optimize performance-critical applications across many scientific domains by finding the best program variant among many choices. Efficient optimization algorithms are crucial for navigating the vast and complex search spaces in auto-tuning. As is well known in the context of machine learning and similar fields, hyperparameters critically shape optimization algorithm efficiency. Y et for auto-tuning frameworks, these hyperparameters are almost never tuned, and their potential performance impact has not been studied. We present a novel method for general hyperparameter tuning of optimization algorithms for auto-tuning, thus "tuning the tuner". In particular, we propose a robust statistical method for evaluating hyperparameter performance across search spaces, publish a F AIR data set and software for reproducibility, and present a simulation mode that replays previously recorded tuning data, lowering the costs of hyperparameter tuning by two orders of magnitude. We show that even limited hyperparam-eter tuning can improve auto-tuner performance by 94.8% on average, and establish that the hyperparameters themselves can be optimized efficiently with meta-strategies (with an average improvement of 204.7%), demonstrating the often overlooked hyperparameter tuning as a powerful technique for advancing auto-tuning research and practice. UTOMA TIC performance tuning, or auto-tuning, is a widely established method for optimizing the performance of applications in many scientific domains, including radio astronomy [1]-[4], image processing [5]-[7], fluid dynamics [8]-[10], and climate modeling [11]-[13]. Auto-tuning automates the process of exploring the myriad of implementation choices that arise in performance optimization, such as the number of threads, tile sizes used in loop blocking, and other code optimization parameters [14]. At the heart of the auto-tuning method is a search space of functionally-equivalent code variants that is explored by an optimization algorithm.

Despite these advancements, QAOA's practical efficacy is challenged by the quantum coherence limits of modern quantum devices, as there is a ceiling on the allowable maximum circuit depth

LLMs possess a vast reservoir of knowledge, which remains under-utilized in current finetuning-based approaches.

Warning: This paper contains unfiltered and potentially harmful content.