{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T14:38:35Z","timestamp":1787582315169,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032362162","type":"print"},{"value":"9783032362179","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-36217-9_27","type":"book-chapter","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T13:59:34Z","timestamp":1787579974000},"page":"433-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Model Merging to\u00a0Evolution: Parameter Space Exploration for\u00a0Expert Models"],"prefix":"10.1007","author":[{"given":"Chao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanchun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbiao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiqi","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"issue":"2","key":"27_CR1","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s42256-024-00975-8","volume":"7","author":"T Akiba","year":"2025","unstructured":"Akiba, T., Shing, M., Tang, Y., Sun, Q., Ha, D.: Evolutionary optimization of model merging recipes. Nat. Mach. Intell. 7(2), 195\u2013204 (2025)","journal-title":"Nat. Mach. Intell."},{"key":"27_CR2","unstructured":"Austin, J., et al.: Program synthesis with large language models. arXiv preprint arXiv:2108.07732 (2021)"},{"key":"27_CR3","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020)"},{"key":"27_CR4","unstructured":"Clark, P., et al.: Think you have solved question answering? Try arc, the AI2 reasoning challenge. arXiv preprint arXiv:1803.05457 (2018)"},{"key":"27_CR5","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Dua, D., Wang, Y., Dasigi, P., Stanovsky, G., Singh, S., Gardner, M.: DROP: a reading comprehension benchmark requiring discrete reasoning over paragraphs. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 2368\u20132378. Association for Computational Linguistics, Minneapolis, Minnesota (2019)","DOI":"10.18653\/v1\/N19-1246"},{"issue":"7553","key":"27_CR7","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1038\/nature14544","volume":"521","author":"AE Eiben","year":"2015","unstructured":"Eiben, A.E., Smith, J.: From evolutionary computation to the evolution of things. Nature 521(7553), 476\u2013482 (2015)","journal-title":"Nature"},{"key":"27_CR8","unstructured":"Feng, S., et al.: Model swarms: collaborative search to adapt LLM experts via swarm intelligence. In: Forty-Second International Conference on Machine Learning (2025)"},{"key":"27_CR9","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1162\/tacl_a_00474","volume":"10","author":"N Goyal","year":"2022","unstructured":"Goyal, N., et al.: The Flores-101 evaluation benchmark for low-resource and multilingual machine translation. Trans. Assoc. Comput. Linguist. 10, 522\u2013538 (2022)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"27_CR10","unstructured":"Hansen, N.: The CMA evolution strategy: a tutorial. arXiv preprint arXiv:1604.00772 (2016)"},{"key":"27_CR11","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: International Conference on Learning Representations (2021)"},{"key":"27_CR12","unstructured":"Hendrycks, D., et al.: Measuring mathematical problem solving with the MATH dataset. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021)"},{"key":"27_CR13","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"27_CR14","unstructured":"Huang, C., Liu, Q., Lin, B.Y., Pang, T., Du, C., Lin, M.: Lorahub: efficient cross-task generalization via dynamic loRA composition. In: First Conference on Language Modeling (2024)"},{"key":"27_CR15","unstructured":"Ilharco, G., Ribeiro, M.T., Wortsman, M., Schmidt, L., Hajishirzi, H., Farhadi, A.: Editing models with task arithmetic. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"27_CR16","unstructured":"Ivison, H., et al.: Camels in a changing climate: enhancing LM adaptation with tulu 2. arXiv preprint arXiv:2311.10702 (2023)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Matena, M.S., et al.: Merging models with fisher-weighted averaging. In: Oh, A. (ed.) Advances in Neural Information Processing Systems, vol. 35, pp. 17703\u201317716. Curran Associates, Inc. (2022)","DOI":"10.52202\/068431-1287"},{"key":"27_CR18","unstructured":"Mavromatis, C., Karypis, P., Karypis, G.: Pack of LLMs: model fusion at test-time via perplexity optimization. In: First Conference on Language Modeling (2024)"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Miikkulainen, R.: Neuroevolution insights into biological neural computation. Science 387(6735), eadp7478 (2025)","DOI":"10.1126\/science.adp7478"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Minut, A.R., Mencattini, T., Santilli, A., Crisostomi, D., Rodol\u00e0, E.: Mergenetic: a simple evolutionary model merging library. In: Mishra, P., Muresan, S., Yu, T. (eds.) Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pp. 572\u2013582. Association for Computational Linguistics, Vienna, Austria (2025)","DOI":"10.18653\/v1\/2025.acl-demo.55"},{"key":"27_CR21","unstructured":"Mirzadeh, S.I., Alizadeh, K., Shahrokhi, H., Tuzel, O., Bengio, S., Farajtabar, M.: GSM-symbolic: understanding the limitations of mathematical reasoning in large language models. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., Mihalcea, R.: MELD: a multimodal multi-party dataset for emotion recognition in conversations. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 527\u2013536. Association for Computational Linguistics, Florence, Italy (2019)","DOI":"10.18653\/v1\/P19-1050"},{"key":"27_CR23","unstructured":"Salimans, T., Ho, J., Chen, X., Sidor, S., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. arXiv preprint arXiv:1703.03864 (2017)"},{"key":"27_CR24","unstructured":"Shi, F., et al.: Language models are multilingual chain-of-thought reasoners. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Suzgun, M., et al.: Challenging BIG-bench tasks and whether chain-of-thought can solve them. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Findings of the Association for Computational Linguistics: ACL 2023, pp. 13003\u201313051. Association for Computational Linguistics, Toronto, Canada (2023)","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"27_CR26","unstructured":"Talmor, A., Herzig, J., Lourie, N., Berant, J.: CommonsenseQA: a question answering challenge targeting commonsense knowledge. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4149\u20134158. Association for Computational Linguistics, Minneapolis, Minnesota (2019)"},{"key":"27_CR27","unstructured":"Riviere, M., et al.: Gemma 2: improving open language models at a practical size. arXiv preprint arXiv:2408.00118 (2024)"},{"key":"27_CR28","doi-asserted-by":"publisher","first-page":"0646","DOI":"10.34133\/research.0646","volume":"8","author":"C Wang","year":"2025","unstructured":"Wang, C., Zhao, J., Jiao, L., Li, L., Liu, F., Yang, S.: When large language models meet evolutionary algorithms: potential enhancements and challenges. Research 8, 0646 (2025)","journal-title":"Research"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Mmlu-pro: a more robust and challenging multi-task language understanding benchmark. In: Globerson, A., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a037, pp. 95266\u201395290. Curran Associates, Inc. (2024)","DOI":"10.52202\/079017-3018"},{"key":"27_CR30","unstructured":"Wang, Z., et al.: Why do more experts fail? A theoretical analysis of model merging. arXiv preprint arXiv:2505.21226 (2025)"},{"issue":"1","key":"27_CR31","first-page":"949","volume":"15","author":"D Wierstra","year":"2014","unstructured":"Wierstra, D., Schaul, T., Glasmachers, T., Sun, Y., Peters, J., Schmidhuber, J.: Natural evolution strategies. J. Mach. Learn. Res. 15(1), 949\u2013980 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"27_CR32","unstructured":"Wortsman, M., et al.: Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 23965\u201323998. PMLR (2022)"},{"key":"27_CR33","doi-asserted-by":"publisher","first-page":"7093","DOI":"10.52202\/075280-0310","volume":"36","author":"P Yadav","year":"2023","unstructured":"Yadav, P., Tam, D., Choshen, L., Raffel, C.A., Bansal, M.: Ties-merging: resolving interference when merging models. Adv. Neural. Inf. Process. Syst. 36, 7093\u20137115 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Yang, E., et al.: Model merging in LLMs, MLLMs, and beyond: methods, theories, applications, and opportunities. ACM Comput. Surv. 58(8) (2026)","DOI":"10.1145\/3787849"},{"key":"27_CR35","unstructured":"Zahiri, S.M., Choi, J.D.: Emotion detection on tv show transcripts with sequence-based convolutional neural networks. arXiv preprint arXiv:1708.04299 (2018)"},{"key":"27_CR36","unstructured":"Zhang, Y., et al.: Nature-inspired population-based evolution of large language models. arXiv preprint arXiv:2503.01155 (2025)"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Zhang, R., Zhang, J., Ye, Y., Luo, Z.: LlamaFactory: unified efficient fine-tuning of 100+ language models. In: Cao, Y., Feng, Y., Xiong, D. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pp. 400\u2013410. Association for Computational Linguistics, Bangkok, Thailand (2024)","DOI":"10.18653\/v1\/2024.acl-demos.38"}],"container-title":["Lecture Notes in Computer Science","Parallel Problem Solving from Nature \u2013 PPSN XIX"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36217-9_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T13:59:38Z","timestamp":1787579978000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36217-9_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"ISBN":["9783032362162","9783032362179"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36217-9_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,25]]},"assertion":[{"value":"25 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"PPSN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Problem Solving from Nature","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Trento","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ppsn2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}