[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82051-en":3,"doc-seo-82051-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82051,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","LLM-Driven Evolutionary Generation of Multi-Objective Bayesian Optimization Algorithms","Designing effective multi-objective Bayesian optimization (MOBO) algorithms requires balancing interdependent design choices that depend on the specific problem and usually demand deep expertise. This work extends the LLaMEA framework to MOBO by using large language models as mutation and crossover operators inside evolutionary strategies, with SMAC hyperparameter optimization integrated into the evolutionary loop. Across nine runs, ~900 algorithms are generated and benchmarked on twelve synthetic problems and three real-world engineering problems. Generated methods achieve higher mean normalized hypervolume than a BoFire qParEGO baseline while using substantially less wall-clock time.","arXiv :2607 .0879 1v 1 [ cs .NE] 6 Jul 2026  \nLLM-Driven Evolutionary Generation of Multi-Objective Bayesian Optimization Algorithms  \nG. Laskaris, 1, 2 R. Brasher, 1 N. van Stein,2 E. Raponi,2 T. B¨ack, 1, 2 and F. Neukart 1, 2  \n1 Terra Quantum AG, Kornhausstrasse 25, 9000 St. Gallen, Switzerland  \n2 LIACS, Leiden University, Leiden, Netherlands  \nDesigning effective multi-objective Bayesian optimization (MOBO) algorithms requires balancing many interdependent design choices whose optimal configuration is problem-dependent and typically demands deep expertise. We extend the LLaMEA framework to MOBO, using large language models as mutation and crossover operators within evolutionary strategies to generate complete algorithm implementations, with SMAC hyperparameter optimization integrated into the evolutionary loop. Across nine evolutionary runs we generated approximately 900 algorithms and benchmarked them on twelve synthetic problems (ZDT, DTLZ, WFG) and three real-world engineering problems (RE), using a BoFire qParEGO implementation as a state-of-the-art Bayesian-optimization baseline. On the synthetic suite the strongest generated algorithm attains the highest mean normalized hypervolume (0.971, vs. 0.869 for qParEGO) while requiring roughly 60 × less wall-clock time; a Friedman test with post-hoc analysis places the two in a single top-performing group, and per-problem tests find the generated algorithm significantly better than qParEGO on 7 of the 12 problems and never worse, matching state-of-the-art accuracy at an order-of-magnitude lower cost. On the three unseen real-world engineering problems a generated algorithm attains the best mean normalized hypervolume (0.985, vs. 0.971 for qParEGO)—significantly better than qParEGO on two of the three problems—at roughly 3.4 × lower wall-clock cost, confirming that the gains transfer beyond the synthetic regime. LLM-driven evolutionary search can thus discover algorithm designs that achieve Pareto-efficient trade-offs difficult to reach through manual design.  \nI. INTRODUCTION  \nMulti-objective optimization (MOO) problems arise naturally across science and engineering with extensive applications to drug design [1, 2] and structural engineering [3, 4] among others. When the objective functions are expensive to evaluate, Bayesian optimization (BO) [5, 6] offers a framework for Pareto-optimal solutions with limited budget. Designing an effective multiobjective Bayesian optimization (MOBO) algorithm remains a challenge since there are numerous interdependent design choices. The best configuration is often problem-dependent, requiring deep expertise and extensive empirical tuning.  \nRecent work on LLM-driven algorithm generation [7– 11] has shown that large language models, coupled with evolutionary search, can automatically design optimization algorithms competitive with human-designed alternatives—going beyond parameter tuning to synthesize new algorithms.  \nLLaMEA-BO [12] is an automated method that uses large language models as variation operators within an evolutionary loop to design complete Bayesian optimization algorithms. In this work, we extend it to the multiobjective setting, with the discovered algorithms as the object of study. We frame the work as an extension of the LLaMEA framework rather than as a new automateddesign paradigm: our contribution is the MOBO generation loop and the concrete, competitive algorithms it produces, which we benchmark against established handdesigned MOBO methods. Our contributions are as follows:  \n• We extend the LLaMEA framework [10, 12] to the multi-objective Bayesian optimization setting, generating and configuring complete MOBO algorithms with normalized hypervolume across a suite of synthetic and real-world problems as the fitness signal. Following the LLaMEA-HPO methodology [13], we integrate SMAC-based hyperparameter optimization directly into the evolutionary loop, implemented within our own multi-objective pipeline.  \n• We be","cbCaiheu8irjfsWh","https://ap.wps.com/l/cbCaiheu8irjfsWh","pdf",6598142,1,21,"English","en",105,"# Introduction\n## Multi-objective optimization and Bayesian optimization\n## LLM-driven algorithm generation\n## LLaMEA-BO extension and contributions","[{\"question\":\"What problem does this work address in multi-objective Bayesian optimization?\",\"answer\":\"It addresses the challenge of designing effective MOBO algorithms, where many interdependent design choices must be configured in a problem-dependent way and typically require extensive expertise and tuning.\"},{\"question\":\"How are large language models used in the proposed method?\",\"answer\":\"Large language models act as mutation and crossover operators within evolutionary strategies, generating complete MOBO algorithm implementations rather than only tuning parameters.\"},{\"question\":\"How does the generated approach perform compared with the qParEGO baseline?\",\"answer\":\"On synthetic problems, the best generated algorithm reaches higher mean normalized hypervolume (0.971 vs. 0.869) and uses about 60× less wall-clock time. On real-world engineering problems, the top generated algorithm achieves best mean normalized hypervolume (0.985 vs. 0.971) with roughly 3.4× lower wall-clock cost.\"}]",1784177826,53,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"llm-driven-evolutionary-generation-of-multi-objective-bayesian-optimization-algorithms","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/llm-driven-evolutionary-generation-of-multi-objective-bayesian-optimization-algorithms/82051/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does this work address in multi-objective Bayesian optimization?","Question",{"text":74,"@type":75},"It addresses the challenge of designing effective MOBO algorithms, where many interdependent design choices must be configured in a problem-dependent way and typically require extensive expertise and tuning.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How are large language models used in the proposed method?",{"text":79,"@type":75},"Large language models act as mutation and crossover operators within evolutionary strategies, generating complete MOBO algorithm implementations rather than only tuning parameters.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the generated approach perform compared with the qParEGO baseline?",{"text":83,"@type":75},"On synthetic problems, the best generated algorithm reaches higher mean normalized hypervolume (0.971 vs. 0.869) and uses about 60× less wall-clock time. On real-world engineering problems, the top generated algorithm achieves best mean normalized hypervolume (0.985 vs. 0.971) with roughly 3.4× lower wall-clock cost.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]