Recently, evolutionary multitasking (EMT) has been proposed in the field of computation as a new search paradigm, for solving multiple optimization tasks simultaneously. By sharing useful traits found along process across different tasks, performance on each task could be enhanced. The autoencoding-based EMT is recently algorithm. In contrast to most existing algorithms, which conduct knowledge transfer implicitly via crossover, it intends perform explicitly among form solutions, enables...

Vehicle routing problems (VRPs) are essential in logistics. In the literature, many exact and heuristic optimization algorithms have been proposed to solve VRPs. These traditional approaches, however, generally start from scratch ignore experiences of solving related VRPs, which may lead unnecessary computational costs searching repeated reduce efficiency vehicle routing. Recently, transfer (TO) has presented speed up by reusing knowledge learned similarly solved However, existing TO methods...

The Vehicle Routing Problem (VRP) is a well-known NP-hard combinatorial optimization problem, which has wide spread applications in real world, such as logistics, bus route planning, and urban path planning. To solve VRP, traditional methods usually start the search from scratch ignore VRPs solved past, could lead to repeated explorations of space related problems, thus results slow process involving unnecessary computational cost. Keeping this mind, speed up for vehicle routing, article...

Recently, large language models (LLMs) have notably positioned them as capable tools for addressing complex optimization challenges. Despite this recognition, a predominant limitation of existing LLM-based methods is their struggle to capture the relationships among decision variables when relying exclusively on numerical text prompts, especially in high-dimensional problems. Keeping mind, we first propose enhance performance using multimodal LLM processing both textual and visual prompts...

Evolutionary multitasking (EMT), which shares knowledge across multiple tasks while the optimization progresses online, has demonstrated superior performance in terms of both quality and convergence speed over its single-task counterpart solving complex problems. However, most existing EMT algorithms only consider handling two simultaneously. As computational cost incurred evolutionary search transfer increased rapidly with number tasks, these cannot meet today's requirements service on...

Evolutionary multitasking (EMT) has attracted much attention in the community of evolutionary computation recently. It intends to improve performance optimization on multiple problems via knowledge learning and transfer across them while processes progress online. Existing EMT paradigms can be classified as explicit (EEMT) implicit (IEMT) according mechanisms adopted transfer. With additional modules, EEMT often brings flexible algorithmic designs effective against IEMT. However, most...

Multi-objective optimization problems (MOPs) are prevalent in various real-world applications, necessitating sophisticated solutions that balance conflicting objectives. Traditional evolutionary algorithms (EAs), while effective, often rely on domain-specific expert knowledge and iterative tuning, which can impede innovation when encountering novel MOPs. Very recently, the emergence of Large Language Models (LLMs) has revolutionized software engineering by enabling autonomous development...

Evolutionary multitasking (EMT) is an emerging approach for solving multitask optimization problems (MTOPs) and has garnered considerable research interest. The implicit EMT a significant branch that utilizes evolution operators to enable knowledge transfer (KT) between tasks. However, current approaches in face challenges adaptability, due the use of limited number insufficient utilization evolutionary states performing KT. This results suboptimal exploitation KT's potential tackle variety...

With the rapid advancement of Neural Machine Translation (NMT), enhancing translation efficiency and quality has become a focal point research. Despite commendable performance general models such as Transformer in various aspects, they still fall short processing long sentences fully leveraging bidirectional contextual information. This paper introduces an improved model based on Transformer, implementing asynchronous segmented decoding strategy aimed at elevating accuracy. Compared to...

With the rapid advancement of Neural Machine Translation (NMT), enhancing translation efficiency and quality has become a focal point research. Despite commendable performance general models such as Transformer in various aspects, they still fall short processing long sentences fully leveraging bidirectional contextual information. This paper introduces an improved model based on Transformer, implementing asynchronous segmented decoding strategy aimed at elevating accuracy. Compared to...

Evolutionary Multi-task Optimization (EMTO) is a paradigm that leverages knowledge transfer across simultaneously optimized tasks for enhanced search performance. To facilitate EMTO's performance, various models have been developed specific optimization tasks. However, designing these often requires substantial expert knowledge. Recently, large language (LLMs) achieved remarkable success in autonomous programming, aiming to produce effective solvers problems. In this work, LLM-based...

Evolutionary Multi-Tasking (EMT), which solves multiple optimization tasks simultaneously, is a burgeoning topic in the area of evolutionary computation. As EMT transfers useful knowledge across to guide search while process progresses online, superior performance has been obtained many recent attempts. Autoencoding multitasking recently proposed algorithm, employs single-layer denoising auto-encoder for transfer. However, since autoencoding (AEEMT) algorithm learns relationships between...

Deep neural network(DNN) generalization is limited by the over-reliance of current offline reinforcement learning techniques on conservative processing existing datasets. This method frequently results in algorithms that settle for suboptimal solutions only adjust to a certain dataset. Similarly, online learning, previously imposed punitive pessimism also deprives model its exploratory potential. Our research proposes novel framework, Optimistic and Pessimistic Actor Reinforcement Learning...