Evolution Strategy Research Articles

High Thermoelectric Performance in Rhombohedral GeSe-LiBiTe2.

GeSe, an analogue of SnSe, shows promise in exhibiting exceptional thermoelectric performance in the Pnma phase. The constraints on its dopability, however, pose challenges in attaining optimal carrier concentrations and improving ZT values. This study demonstrates a crystal structure evolution strategy for achieving highly doped samples and promising ZTs in GeSe via LiBiTe2 alloying. A rhombohedral phase (R3m) can be stabilized in the GeSe-LiBiTe2 system, further evolving into a cubic (Fm3̅m) phase with a rising temperature. The band structures of GeSe-LiBiTe2 in the rhombohedral and cubic phases feature a similar multiple-valley energy-converged valence band of L and Σ bands. The observed high carrier concentration (∼1020 cm-3) reflects the effective convergence of these bands, enabling a high density-of-states effective mass and an enhanced power factor. Moreover, a very low lattice thermal conductivity of 0.6-0.5 W m-1 K-1 from 300 to 723 K is achieved in 0.9GeSe-0.1LiBiTe2, approaching the amorphous limit value. This remarkably low lattice thermal conductivity is related to phonon scattering from point defects, planar vacancies, and ferroelectric instability-induced low-energy Einstein oscillators. Finally, a maximum ZT value of 1.1 to 1.3 at 723 K is obtained, with a high average ZT value of over 0.8 (400-723 K) in 0.9GeSe-0.1LiBiTe2 samples. This study establishes a viable route for tailoring crystal structures to significantly improve the performance of GeSe-related compounds.

Optimization Of Cantilever Retaining Wall Design Using Improved Teaching-Learning-Based Optimization Algorithms

Retaining structures play a crucial role in geotechnical engineering to support soil levels, prevent slope failure, and create flat surfaces for construction. Designing these structures involves optimizing internal and external stability while minimizing material usage and cost. This study focused on optimizing reinforced concrete cantilever retaining walls using the Teaching-Learning Based Optimization (TLBO) algorithm and an improved version (I-TLBO) with agents. In the context of the study, geometric-structural design variables, geotechnical -structural constraints, and optimization processes were examined. Minimizing weight and minimizing cost of the wall were the objectives considered in the cantilever retaining wall design process. The optimization results were compared with other algorithms in the literature, such as genetic algorithms, evolutionary strategies, and particle swarm optimization. The improved TLBO algorithm demonstrated superior performance, achieved lower design dimensions, and reduced costs. It provided more efficient solutions that pushed design constraints closer to their limits, resulting in a cost-effective and structurally sound cantilever retaining wall design. As a result of the study, the I-TLBO algorithm was found to be more cost and weight-effective than other methods in the optimization of cantilever retaining wall design.

Topological design of microstructured materials using energy-based homogenization theory and proportional topology optimization with the level-set method

In this study, we propose a novel approach to designing microstructures of porous material with extreme mechanical properties to maximize the bulk or shear modulus. The approach integrates energy-based homogenization theory and proportional topology optimization with the level-set method (HPTO-LSM). A level-set function (LSF) evolution strategy based on the nodal element mutual energies (EME) proportion is proposed and drives the LSF’s evolution. An EME proportion filtering technique is proposed and reduces the redundant branch structure. And a linear scaling strategy is applied to the HPTO-LSM to enhance the topological change ability. The effectiveness of the HPTO-LSM for designing microstructures of cellular materials to maximize the bulk or shear modulus is demonstrated using several 2D and 3D cases. The effects (changes in objective function values or topologies) of the EME proportion filtering scheme and scaling strategy on the HPTO-LSM are discussed. In addition, we compared the HPTO-LSM method with the solid isotropic material with penalization (SIMP) and bi-directional evolutionary structural optimization (BESO) methods through numerical examples. As shown by the results, effective objective function values and 2D and 3D microstructural topologies with clear interfaces and smooth boundaries can be acquired using the new approach. Applying the EME proportion filtering scheme and scaling strategy in the HPTO-LSM not only enhanced the topological variation of microstructures but also facilitated the acquisition of microstructures conducive to engineering applications. Compared to the SIMP and BESO methods, the HPTO-LSM method has significant advantages in obtaining better objective function values and better microstructural topologies.

Autotrophic adaptive laboratory evolution of the acetogen Clostridium autoethanogenum delivers the gas-fermenting strain LAbrini with superior growth, products, and robustness

Microbes able to convert gaseous one-carbon (C1) waste feedstocks are increasingly important to transition to the sustainable production of renewable chemicals and fuels. Acetogens are interesting biocatalysts since gas fermentation using Clostridium autoethanogenum has been commercialised. However, most acetogen strains need complex nutrients, display slow growth, and are not robust for bioreactor fermentations. In this work, we used three different and independent adaptive laboratory evolution (ALE) strategies to evolve the wild-type C. autoethanogenum to grow faster, without yeast extract and to be robust in operating continuous bioreactor cultures. Multiple evolved strains with improved phenotypes were isolated on minimal media with one strain, named “LAbrini”, exhibiting superior performance regarding the maximum specific growth rate, product profile, and robustness in continuous cultures. Whole-genome sequencing of the evolved strains identified 25 mutations. Of particular interest are two genes that acquired seven different mutations across the three ALE strategies, potentially as a result of convergent evolution. Reverse genetic engineering of mutations in potentially sporulation-related genes CLAU_3129 (spo0A) and CLAU_1957 recovered all three superior features of our ALE strains through triggering significant proteomic rearrangements. This work provides a robust C. autoethanogenum strain “LAbrini” to accelerate phenotyping and genetic engineering and to better understand acetogen metabolism.

PAAD: Panelization algorithm for architectural designs.

Due to the competitive nature of the construction industry, the efficiency of requirement analysis is important in enhancing client satisfaction and a company's reputation. For example, determining the optimal configuration of panels (generally called panelization) that form the structure of a building is one aspect of cost estimation. However, existing methods typically rely on rule-based approaches that may lead to suboptimal material usage, particularly in complex designs featuring angled walls and openings. Such inefficiency can increase costs and environmental impact due to unnecessary material waste. To address these challenges, this research proposes a Panelization Algorithm for Architectural Designs, referred to as PAAD, which utilizes a genetic evolutionary strategy built on the 2D bin packing problem. This method is designed to balance between strict adherence to manufacturing constraints and the objective of optimizing material usage. PAAD starts with multiple potential solutions within the predefined problem space, facilitating dynamic exploration of panel configurations. It approaches structural rules as flexible constraints, making necessary corrections in post-processing, and through iterative developments, the algorithm refines panel sets to minimize material use. The methodology is validated through an analysis against an industry implementation and expert-derived solutions, highlighting PAAD's ability to surpass existing results and reduce the need for manual corrections. Additionally, to motivate future research, a synthetic data generator, the architectural drawing encodings used, and a preliminary interface are also introduced. This not only highlights the algorithm's practical applicability but also encourages its use in real-world scenarios.

Directed evolution of hyperactive integrases for site specific insertion of transgenes.

The ability to deliver large transgenes to a single genomic sequence with high efficiency would accelerate biomedical interventions. Current methods suffer from low insertion efficiency and most rely on undesired double-strand DNA breaks. Serine integrases catalyze the insertion of large DNA cargos at attachment (att) sites. By targeting att sites to the genome using technologies such as prime editing, integrases can target safe loci while avoiding double-strand breaks. We developed a method of phage-assisted continuous evolution we call IntePACE, that we used to rapidly perform hundreds of rounds of mutagenesis to systematically improve activity of PhiC31 and Bxb1 serine integrases. Novel hyperactive mutants were generated by combining synergistic mutations resulting in integration of a multi-gene cargo at rates as high as 80% of target chromosomes. Hyperactive integrases inserted a 15.7 kb therapeutic DNA cargo containing Von Willebrand Factor. This technology could accelerate gene delivery therapeutics and our directed evolution strategy can easily be adapted to improve novel integrases from nature.

Performance of Saccharomyces cerevisiae strains against the application of adaptive laboratory evolution strategies for butanol tolerance

Although the industrial production of butanol has been carried out for decades by bacteria of the Clostridium species, recent studies have shown the use of the yeast Saccharomyces cerevisiae as a promising alternative. While the production of n-butanol by this yeast is still very far from its tolerability (up to 2% butanol), the improvement in the tolerance can lead to an increase in butanol production. The aim of the present work was to evaluate the adaptive capacity of the laboratory strain X2180-1B and the Brazilian ethanol-producing strain CAT-1 when submitted to two strategies of adaptive laboratory Evolution (ALE) in butanol. The strains were submitted, in parallel, to ALE with successive passages or with UV irradiation, using 1% butanol as selection pressure. Despite initially showing greater tolerance to butanol, the CAT-1 strain did not show great improvements after being submitted to ALE. Already the laboratory strain X2180-1B showed an incredible increase in butanol tolerance, starting from a condition of inability to grow in 1% butanol, to the capacity to grow in this same condition. With emphasis on the X2180_n100#28 isolated colony that presented the highest maximum specific growth rate among all isolated colonies, we believe that this colony has good potential to be used as a model yeast for understanding the mechanisms that involve tolerance to alcohols and other inhibitory compounds.

2D Porphyrin-Based Covalent-Organic Framework/PEG Composites: A Rational Strategy for Photocatalytic Hydrogen Evolution.

Two-dimensional porphyrin-based covalent-organic frameworks (2D-por-COFs) have gained significant attention as attractive platforms for efficient solar light conversion into hydrogen production. Herein, it is found that introducing transition metal zinc and polyethylene glycol (PEG) into 2D-por-COFs can effectively improve the photocatalytic hydrogen evolution performance. The photocatalytic hydrogen evolution rate of ZnPor-COF is 2.82 times higher than that of H2Por-COF. Moreover, ZnPor-COF@PEG has the highest photocatalytic hydrogen evolution efficiency, which is 1.31 and 3.7 times that of pristine ZnPor-COF and H2Por-COF, respectively. The filling of PEG makes the layered structure of COFs more stable. PEG reduces the distortion and deformation of the carbon skeleton after the experiment of photocatalytic hydrogen evolution. The layered stacking and crystallization of 2D-por-COFs are also enhanced. Meanwhile, the presence of PEG also accelerates the transfer of excited electrons and enhances the photocatalytic hydrogen evolution activity. This strategy will provide valuable insights into the design of 2D-por-COFs as efficient solid photocatalysts for solar-driven hydrogen production.

Abstract IA021: Environmental challenge rewires functional connections among human genes

Abstract A fundamental question in biology is how a limited number of genes combinatorially govern cellular responses to environmental changes. While the prevailing hypothesis is that relationships between genes, processes, and ontologies could be plastic to achieve this adaptability, quantitatively comparing human gene functional connections between specific environmental conditions at scale is very challenging. Therefore, it remains unclear whether and how human genetic interaction networks are rewired in response to changing environmental conditions. Here, we developed a framework for mapping context-specific genetic interactions, enabling us to measure the plasticity of human genetic architecture upon environmental challenge for ∼250,000 interactions, using cell cycle interruption, genotoxic perturbation, and nutrient deprivation as archetypes. We discover large-scale rewiring of human gene relationships across conditions, highlighted by dramatic shifts in the functional connections of epigenetic regulators (TIP60), cell cycle regulators (PP2A), and glycolysis metabolism. Our study demonstrates that upon environmental perturbation, intra-complex genetic rewiring is rare while inter-complex rewiring is common, suggesting a modular and flexible evolutionary genetic strategy that allows a limited number of human genes to enable adaptation to a large number of environmental conditions. Citation Format: Luke Gilbert, Ben Herken. Environmental challenge rewires functional connections among human genes [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Expanding and Translating Cancer Synthetic Vulnerabilities; 2024 Jun 10-13; Montreal, Quebec, Canada. Philadelphia (PA): AACR; Mol Cancer Ther 2024;23(6 Suppl):Abstract nr IA021.

Three-party evolutionary game-based analysis and stability enhancement of improved PBFT consensus mechanism

Three-party evolutionary game-based analysis and stability enhancement of improved PBFT consensus mechanism

Quasi-random Fractal Search (QRFS): A dynamic metaheuristic with sigmoid population decrement for global optimization

Global optimization of complex and high-dimensional functions remains a central challenge with broad applications in science and engineering. This study introduces a new optimization approach called quasi-random metaheuristic based on fractal search (QRFS), which harnesses the power of fractal geometry, low discrepancy sequences, and intelligent search space partitioning techniques. The QRFS uses fractals’ inherent self-similarity and intricate structure to guide the solution space exploration. For the proposal, a deterministic but quasi-random element is used in the search process using low discrepancy sequences, such as Sobol, Halton, Hammersley, and Latin Hypercube. This integration allows the algorithm to systematically cover the search space while maintaining the level of diversity necessary for efficient exploration. The QRFS employs a dynamic strategy of partitioning the search space and reducing the population of solutions to optimize the use of function accesses, which causes it to adapt well to the characteristics of the problem. The algorithm intelligently identifies and prioritizes promising regions within the fractal-based representation, allocating computational resources where they are most likely to yield optimal solutions. Experimental evaluations on several benchmark problems demonstrate that QRFS consistently outperforms modern, canonical metaheuristics and variants of algorithms such as differential evolution (DE), particle swarm optimization (PSO), covariance matrix adaptive evolution strategy (CMA-ES), regarding solution quality. Besides, the algorithm shows remarkable scalability, which makes it suitable for high-dimensional optimization tasks. Overall, QRFS offers a robust and efficient approach to solving complex optimization problems in various domains, paving the way for improved decision-making in real-world applications.

Evolutionary radiation strategy revealed in the Scarabaeidae with evidence of continuous spatiotemporal morphology and phylogenesis

Evolutionary biology faces the important challenge of determining how to interpret the relationship between selection pressures and evolutionary radiation. The lack of morphological evidence on cross-species research adds to difficulty of this challenge. We proposed a new paradigm for evaluating the evolution of branches through changes in characters on continuous spatiotemporal scales, for better interpreting the impact of biotic/abiotic drivers on the evolutionary radiation. It reveals a causal link between morphological changes and selective pressures: consistent deformation signals for all tested characters on timeline, which provided strong support for the evolutionary hypothesis of relationship between scarabs and biotic/abiotic drivers; the evolutionary strategies under niche differentiation, which were manifested in the responsiveness degree of functional morphological characters with different selection pressure. This morphological information-driven integrative approach sheds light on the mechanism of macroevolution under different selection pressures and is applicable to more biodiversity research.

Age of information minimization in UAV-assisted data harvesting networks by multi-agent deep reinforcement curriculum learning

Unmanned Aerial Vehicles (UAVs) are increasingly being used for data harvesting from Wireless Sensor Nodes (SNs). This study aims to minimize the Age of Information (AoI) during data collection, while also considering the energy sustainability of the UAVs. Addressing the challenge of optimizing performance in Multi-Agent Reinforcement Learning (MARL) systems as the number of agents increases, our study introduces a MARL approach combined with curriculum learning and evolutionary strategy. This innovation specifically targets the performance issue in traditional MARL setups when scaling up the number of agents. By applying curriculum learning and evolutionary strategies, our method not only enhances MARL scalability but also integrates energy-efficient charging mechanisms, effectively enhancing system performance in large-scale deployments. Numerical results show that our proposed algorithm outperforms baselines in terms of AoI and charging, proving its effectiveness in managing the complexities of large-scale MARL systems.

Genetic Diversity, Mating System, and Seed Viability Reveal a Trade-Off between Outcrossing and Inbreeding in Pinus yunnanensis var. tenuifolia, an Ecologically Important Conifer Species Growing in a Hot-Dry River Basin Habitat in Southwest China

Revealing the relationship between the mating system (i.e., the outcrossing/inbreeding degree) and the fitness of seeds in tree species under wild conditions is essential for understanding the ecological adaptability and evolutionary stability of the species. This study collected open-pollinated seeds from seven wild populations of Pinus yunnanensis var. tenuifolia that exhibited fragmentation in the Nanpan–Hongshui River basin, an ecologically fragile area in China. The seeds and sprouts (germinated seeds) from 20 families were genotyped (24 seeds and 24 sprouts per family) using twelve microsatellite loci to reveal the genetic diversity, mating status, and effect of inbreeding on the three seed quality indicators (thousand-seed weight, germination rate, and germination potential). The three seed quality indicators differed significantly between families (p < 0.001). Higher values of genetic diversity (except the observed heterozygosity) were observed in the sprout group than those in the seed group. Families from different populations showed a notable genetic differentiation (Φst = 0.12), and a large part of families from the common populations had a high degree of coancestry, which signified that the current habitat fragmentation is limiting gene flow between populations. High levels of outcrossing rates (tm) were observed in both the seed group (tm = 0.974) and the sprout group (tm = 0.978), indicating that a low proportion of seeds were self-fertilized. Although there was a slightly higher single outcrossing rate (ts = 0.888) and a lower proportion of biparental inbreeding (tm − ts = 0.077) in sprouts compared to the seeds (ts = 0.871, tm − ts = 0.091), indicating that a part of inbred seeds were purged during the germination stage, curve fitting between the outcrossing rate and seed quality indicators showed that a certain degree of biparental inbreeding (ts between 0.89 and 0.91 and tm − ts between 0.09 and 0.11) did have a positive effect on seed germination ability. This highlights that excessive inbreeding or outbreeding seems to be unfavorable to seed viability. The peculiar relationship between seed viability and the mating system in P. yunnanensis var. tenuifolia was likely an evolutionary consequence of a trade-off between the nature of mixed mating and its specific ecological niche.

Comparing Robot Controller Optimization Methods on Evolvable Morphologies.

In this paper, we compare Bayesian Optimization, Differential Evolution, and an Evolution Strategy employed as a gait-learning algorithm in modular robots. The motivational scenario is the joint evolution of morphologies and controllers, where "newborn" robots also undergo a learning process to optimize their inherited controllers (without changing their bodies). This context raises the question: How do gait-learning algorithms compare when applied to various morphologies that are not known in advance (and thus need to be treated as without priors)? To answer this question, we use a test suite of twenty different robot morphologies to evaluate our gait-learners and compare their efficiency, efficacy, and sensitivity to morphological differences. The results indicate that Bayesian Optimization and Differential Evolution deliver the same solution quality (walking speed for the robot) with fewer evaluations than the Evolution Strategy. Furthermore, the Evolution Strategy is more sensitive for morphological differences (its efficacy varies more between different morphologies) and is more subject to luck (repeated runs on the same morphology show greater variance in the outcomes).

Neural Architecture Search Using Covariance Matrix Adaptation Evolution Strategy.

Evolution-based neural architecture search methods have shown promising results, but they require high computational resources because these methods involve training each candidate architecture from scratch and then evaluating its fitness, which results in long search time. Covariance Matrix Adaptation Evolution Strategy (CMA-ES) has shown promising results in tuning hyperparameters of neural networks but has not been used for neural architecture search. In this work, we propose a framework called CMANAS which applies the faster convergence property of CMA-ES to the deep neural architecture search problem. Instead of training each individual architecture seperately, we used the accuracy of a trained one shot model (OSM) on the validation data as a prediction of the fitness of the architecture, resulting in reduced search time. We also used an architecture-fitness table (AF table) for keeping a record of the already evaluated architecture, thus further reducing the search time. The architectures are modeled using a normal distribution, which is updated using CMA-ES based on the fitness of the sampled population. Experimentally, CMANAS achieves better results than previous evolution-based methods while reducing the search time significantly. The effectiveness of CMANAS is shown on two different search spaces using four datasets: CIFAR-10, CIFAR-100, ImageNet, and ImageNet16-120. All the results show that CMANAS is a viable alternative to previous evolution-based methods and extends the application of CMA-ES to the deep neural architecture search field.

Adaptive responses to habitat change: Theory and tests with field experiments.

Habitat loss and change are often implicated as the primary causes of species extinction. Although any population can be instantly imperiled by catastrophe, most habitat loss occurs gradually, thus enabling affected individuals an adaptive advantage to occupy the best of their dwindling opportunities. I demonstrate how to infer the advantage between two habitats for any density and frequency-dependent strategy of habitat selection. I explore the concept of an Adaptive Dispersal Strategy Landscape to reveal the Evolutionarily Stable Strategy separately for ideal-free and ideal preemptive habitat selectors. Both solutions reveal an initially counterintuitive expectation that individuals living at high density gain insufficient adaptive advantage to disperse from a deteriorating habitat. Adaptive dispersal is constrained at high density because habitats of better quality are fully occupied. I test the theory with measures of movement and foraging in crossover experiments on a seminatural population of meadow voles. The experiment allowed the voles to choose among patches and between enclosures in which I differentially manipulated food and shelter. Although photographs from an infrared camera documented voles venturing from one habitat to the other, none became resident. Voles preferentially foraged in the richer of the two enclosures, even when I reversed treatments, and they foraged more in patches protected by mulched straw. The adaptive advantage of dispersal using a surrogate fitness proxy based on the voles' giving-up densities mirrored that generated by theory. The convergence between theory and experiment yields much-needed insight into our ability to test, predict, and hopefully resolve, the ecological, evolutionary, and conservation consequences of habitat loss.

Host plant selection is linked to performance in Phthorimaea absoluta (Lepidoptera: Gelechiidae).

The evolution of oviposition preference in insects is considered a key evolutionary strategy in the context of host-plant interaction. It is hypothesized that insects maximize the survival and fitness of the subsequent generations by preferring specific host plant(s), known as the "preference-performance hypothesis." In this study, we tested whether adult host preference reflects the immature performance in an oligophagous insect, Phthorimaea absoluta Meyrick, a rapidly emerging invasive pest in Asia, Africa, and Europe. Based on a preliminary survey of the potential host plants of P. absoluta, we selected 6 Solanaceae species, namely, tomato, potato, eggplant, black nightshade, sweet pepper, and tobacco, for the oviposition preference studies. The results indicated that the tomato was the most preferred host in no-, dual- and multiple-choice assays, followed by potato, eggplant, and black nightshade. Subsequently, the insect life-table parameters were found to be superior on tomato compared to other hosts. The order of oviposition preference on the host plants was strongly correlated with the life-table parameters of P. absoluta. Thus, we provide clear evidence for the preference-performance hypothesis in the host selection behavior of P. absoluta. We also emphasize the necessity of conducting oviposition behavior research at various geographic locations to develop tailor-made integrated pest management programs.

Game analysis on PPP model operation of abandoned mines ecological restoration under the innovation of central government's reward and punishment system in China.

There is a huge funding gap in the abandoned mines ecological restoration in China. It is of great research value to explore how PPP model can better introduce social capital into the low-profit ecological restoration of abandoned mines. Based on the innovation perspective of the central government's reward and punishment system, this paper constructs an evolutionary game model of "local government-social capital", analyzes the interaction and behavior mechanism of core stakeholders in the operation process of abandoned mines ecological restoration PPP mode, and discusses the influence of evolutionary equilibrium strategy and parameters change on evolutionary strategy under different scenarios by Matlab simulation. The research shows that the abandoned mines ecological restoration needs the support of the central government. When the local government lightly punishes the low-quality service of social capital, the central government needs to pay higher costs to promote all parties to actively participate in the operation and supervision of the PPP project. The revenue and cost of government supervision, the operating subsidy for social capital and the cost saved by social capital in providing bad service are the key factors affecting the evolution of the game between government and social capital. Punishment can effectively spur social capital to keep the contract and operate in the project, but the punishment effect will be ineffective without government supervision. Finally, some suggestions are put forward, such as establishing a long-term supervision mechanism and a reasonable income mechanism for PPP projects, increasing penalties for violations, attracting third parties to reduce supervision costs and strengthening communication between the two parties, so as to make the project take into account the economic performance of social capital and the social welfare of government departments, and achieve dual Pareto improvement.

Crossover in mutation oriented norm evolution

Norms are a coordination mechanism. They control agents’ behavior in a multiagent system (MAS) and need to evolve to cope with changing environments. Mutation oriented norm evolution is a strategies for allowing norms to evolve. However, this strategy simply adds some possible trigger condition constraints on the norms, which means that some agents are unable to perform actions. To address this problem, this paper presents a new strategy for norm evolution based on an improved crossover operator. First, this paper presents a power-set approach to improve the integrity of norm evolution. This approach can help ensure that all possible combinations of norms are considered during the analysis, providing a deeper understanding of how norms interact and evolve within a norm set. Then, to improve the efficiency of norm evolution, a trade-off between efficiency and completeness is proposed. This approach reduces the search space and improves efficiency, as not every power set combination needs to be searched; it also ensures completeness. Finally, the crossover operator in this strategy is improved based on the trade-off approach. Specifically, the triggers and expectations of one mutated norm enrich the triggers and expectations of other norms. All of these factors enrich the normative conditions through the trade-off approach. A MAS can take immediate action to adapt to new requirements or problems encountered, and quickly make normative changes and learn to respond appropriately to a new situation. The MAS is able to more clearly understand and learn about causality in the environment during norm evolution, and understand the connection between behavior and outcomes. The proposed strategy is applied to a case study of an unmanned vehicle system. The experimental results show that the trade-off approach has greater completeness and effectiveness in norm evolution. This strategy achieves a more complete and effective autonomous norm evolution. It helps the system achieve its goals better and reach better performance in terms of adaptability, helping it to function better in complex multiagent environments.