{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:07:39Z","timestamp":1775840859570,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792798","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"7724-7732","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-Evolving LLMs via Continual Instruction Tuning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2621-3011","authenticated-orcid":false,"given":"Jiazheng","family":"Kang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1519-3851","authenticated-orcid":false,"given":"Le","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7602-7686","authenticated-orcid":false,"given":"Cheng","family":"Hou","sequence":"additional","affiliation":[{"name":"Researcher, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9496-5917","authenticated-orcid":false,"given":"Zhe","family":"Zhao","sequence":"additional","affiliation":[{"name":"Researcher, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1648-496X","authenticated-orcid":false,"given":"ZhenXiang","family":"Yan","sequence":"additional","affiliation":[{"name":"Researcher, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9607-3551","authenticated-orcid":false,"given":"Ting","family":"Bai","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"e_1_3_2_1_2_1","volume-title":"Efficient Multi-task Prompt Tuning for Recommendation. arXiv preprint arXiv:2408.17214","author":"Bai Ting","year":"2024","unstructured":"Ting Bai, Le Huang, Yue Yu, Cheng Yang, Cheng Hou, Zhe Zhao, and Chuan Shi. 2024. Efficient Multi-task Prompt Tuning for Recommendation. arXiv preprint arXiv:2408.17214 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"Generative adversarial networks: An overview","author":"Creswell Antonia","year":"2018","unstructured":"Antonia Creswell, Tom White, Vincent Dumoulin, Kai Arulkumaran, Biswa Sengupta, and Anil A Bharath. 2018. Generative adversarial networks: An overview. IEEE signal processing magazine, Vol. 35, 1 (2018), 53-65."},{"key":"e_1_3_2_1_4_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"de Masson D'Autume Cyprien","year":"2019","unstructured":"Cyprien de Masson D'Autume, Sebastian Ruder, Lingpeng Kong, and Dani Yogatama. 2019. Episodic memory in lifelong language learning. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_5_1","volume-title":"Loramoe: Revolutionizing mixture of experts for maintaining world knowledge in language model alignment. arXiv preprint arXiv:2312.09979","author":"Dou Shihan","year":"2023","unstructured":"Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Jun Zhao, Wei Shen, Yuhao Zhou, Zhiheng Xi, Xiao Wang, Xiaoran Fan, et al., 2023. Loramoe: Revolutionizing mixture of experts for maintaining world knowledge in language model alignment. arXiv preprint arXiv:2312.09979, Vol. 4, 7 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"A survey on the optimization of large language model-based agents. arXiv preprint arXiv:2503.12434","author":"Du Shangheng","year":"2025","unstructured":"Shangheng Du, Jiabao Zhao, Jinxin Shi, Zhentao Xie, Xin Jiang, Yanhong Bai, and Liang He. 2025. A survey on the optimization of large language model-based agents. arXiv preprint arXiv:2503.12434 (2025)."},{"key":"e_1_3_2_1_7_1","unstructured":"Huan-ang Gao Jiayi Geng Wenyue Hua Mengkang Hu Xinzhe Juan Hongzhang Liu Shilong Liu Jiahao Qiu Xuan Qi Yiran Wu et al. 2025. A survey of self-evolving agents: On path to artificial super intelligence. arXiv preprint arXiv:2507.21046 (2025)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.66"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_10_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_11_1","volume-title":"Corpusbrain: A continual generative pre-training framework for knowledge-intensive language tasks. arXiv preprint arXiv:2402.16767","author":"Guo Jiafeng","year":"2024","unstructured":"Jiafeng Guo, Changjiang Zhou, Ruqing Zhang, Jiangui Chen, Maarten de Rijke, Yixing Fan, and Xueqi Cheng. 2024. Corpusbrain: A continual generative pre-training framework for knowledge-intensive language tasks. arXiv preprint arXiv:2402.16767 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Continual pre-training of large language models: How to (re) warm your model? arXiv preprint arXiv:2308.04014","author":"Gupta Kshitij","year":"2023","unstructured":"Kshitij Gupta, Benjamin Th\u00e9rien, Adam Ibrahim, Mats L Richter, Quentin Anthony, Eugene Belilovsky, Irina Rish, and Timoth\u00e9e Lesort. 2023. Continual pre-training of large language models: How to (re) warm your model? arXiv preprint arXiv:2308.04014 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Continual instruction tuning for large multimodal models. arXiv preprint arXiv:2311.16206","author":"He Jinghan","year":"2023","unstructured":"Jinghan He, Haiyun Guo, Ming Tang, and Jinqiao Wang. 2023. Continual instruction tuning for large multimodal models. arXiv preprint arXiv:2311.16206 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"Polymath: A Self-Optimizing Agent with Dynamic Hierarchical Workflow. arXiv preprint arXiv:2508.02959","author":"Ho Chia-Tung","year":"2025","unstructured":"Chia-Tung Ho, Jing Gong, Xufeng Yao, Yunsheng Bai, Abhishek B Akkur, and Haoxing Ren. 2025. Polymath: A Self-Optimizing Agent with Dynamic Hierarchical Workflow. arXiv preprint arXiv:2508.02959 (2025)."},{"key":"e_1_3_2_1_15_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_16_1","volume-title":"Continual learning for text classification with information disentanglement based regularization. arXiv preprint arXiv:2104.05489","author":"Huang Yufan","year":"2021","unstructured":"Yufan Huang, Yanzhe Zhang, Jiaao Chen, Xuezhi Wang, and Diyi Yang. 2021. Continual learning for text classification with information disentanglement based regularization. arXiv preprint arXiv:2104.05489 (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering.. In EMNLP (1). 6769-6781."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.550"},{"key":"e_1_3_2_1_19_1","volume-title":"Continual pre-training of language models. arXiv preprint arXiv:2302.03241","author":"Ke Zixuan","year":"2023","unstructured":"Zixuan Ke, Yijia Shao, Haowei Lin, Tatsuya Konishi, Gyuhak Kim, and Bing Liu. 2023. Continual pre-training of language models. arXiv preprint arXiv:2302.03241 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Adapting BERT for continual learning of a sequence of aspect sentiment classification tasks. arXiv preprint arXiv:2112.03271","author":"Ke Zixuan","year":"2021","unstructured":"Zixuan Ke, Hu Xu, and Bing Liu. 2021b. Adapting BERT for continual learning of a sequence of aspect sentiment classification tasks. arXiv preprint arXiv:2112.03271 (2021)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_1_22_1","volume-title":"PhaseNAS: Language-Model Driven Architecture Search with Dynamic Phase Adaptation. arXiv preprint arXiv:2507.20592","author":"Kong Fei","year":"2025","unstructured":"Fei Kong, Xiaohan Shan, Yanwei Hu, and Jianmin Li. 2025. PhaseNAS: Language-Model Driven Architecture Search with Dynamic Phase Adaptation. arXiv preprint arXiv:2507.20592 (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"Mixlora: Enhancing large language models fine-tuning with lora-based mixture of experts. arXiv preprint arXiv:2404.15159","author":"Li Dengchun","year":"2024","unstructured":"Dengchun Li, Yingzi Ma, Naizheng Wang, Zhengmao Ye, Zhiyuan Cheng, Yinghao Tang, Yan Zhang, Lei Duan, Jie Zuo, Cal Yang, et al., 2024. Mixlora: Enhancing large language models fine-tuning with lora-based mixture of experts. arXiv preprint arXiv:2404.15159 (2024)."},{"key":"e_1_3_2_1_24_1","first-page":"43447","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","volume":"36","author":"Lu Pan","year":"2023","unstructured":"Pan Lu, Baolin Peng, Hao Cheng, Michel Galley, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, and Jianfeng Gao. 2023. Chameleon: Plug-and-play compositional reasoning with large language models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 43447-43478.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","volume-title":"GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks. arXiv preprint arXiv:2502.14848","author":"Luo Jianwen","year":"2025","unstructured":"Jianwen Luo, Yiming Huang, Jinxiang Meng, Fangyu Lei, Shizhu He, Xiao Liu, Shanshan Jiang, Bin Dong, Jun Zhao, and Kang Liu. 2025. GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks. arXiv preprint arXiv:2502.14848 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"Mitigating catastrophic forgetting in task-incremental continual learning with adaptive classification criterion. arXiv preprint arXiv:2305.12270","author":"Luo Yun","year":"2023","unstructured":"Yun Luo, Xiaotian Lin, Zhen Yang, Fandong Meng, Jie Zhou, and Yue Zhang. 2023. Mitigating catastrophic forgetting in task-incremental continual learning with adaptive classification criterion. arXiv preprint arXiv:2305.12270 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_1_28_1","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume":"36","author":"Madaan Aman","year":"2023","unstructured":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al., 2023. Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems, Vol. 36 (2023), 46534-46594.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","volume-title":"Continual learning for natural language generation in task-oriented dialog systems. arXiv preprint arXiv:2010.00910","author":"Mi Fei","year":"2020","unstructured":"Fei Mi, Liangwei Chen, Mengjie Zhao, Minlie Huang, and Boi Faltings. 2020. Continual learning for natural language generation in task-oriented dialog systems. arXiv preprint arXiv:2010.00910 (2020)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17600"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.220"},{"key":"e_1_3_2_1_32_1","volume-title":"Progressive Prompts: Continual Learning for Language Models. In The Eleventh International Conference on Learning Representations.","author":"Razdaibiedina Anastasia","unstructured":"Anastasia Razdaibiedina, Yuning Mao, Rui Hou, Madian Khabsa, Mike Lewis, and Amjad Almahairi. [n.d.]. Progressive Prompts: Continual Learning for Language Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"e_1_3_2_1_34_1","volume-title":"Progressive neural networks. arXiv preprint arXiv:1606.04671","author":"Rusu Andrei A","year":"2016","unstructured":"Andrei A Rusu, Neil C Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, and Raia Hadsell. 2016. Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)."},{"key":"e_1_3_2_1_35_1","volume-title":"Lamol: Language modeling for lifelong language learning. arXiv preprint arXiv:1909.03329","author":"Sun Fan-Keng","year":"2019","unstructured":"Fan-Keng Sun, Cheng-Hao Ho, and Hung-Yi Lee. 2019a. Lamol: Language modeling for lifelong language learning. arXiv preprint arXiv:1909.03329 (2019)."},{"key":"e_1_3_2_1_36_1","volume-title":"Lamol: Language modeling for lifelong language learning. arXiv preprint arXiv:1909.03329","author":"Sun Fan-Keng","year":"2019","unstructured":"Fan-Keng Sun, Cheng-Hao Ho, and Hung-Yi Lee. 2019b. Lamol: Language modeling for lifelong language learning. arXiv preprint arXiv:1909.03329 (2019)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_1_38_1","volume-title":"A survey on self-evolution of large language models. arXiv preprint arXiv:2404.14387","author":"Tao Zhengwei","year":"2024","unstructured":"Zhengwei Tao, Ting-En Lin, Xiancai Chen, Hangyu Li, Yuchuan Wu, Yongbin Li, Zhi Jin, Fei Huang, Dacheng Tao, and Jingren Zhou. 2024. A survey on self-evolution of large language models. arXiv preprint arXiv:2404.14387 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"A comprehensive survey of continual learning: Theory, method and application","author":"Wang Liyuan","year":"2024","unstructured":"Liyuan Wang, Xingxing Zhang, Hang Su, and Jun Zhu. 2024c. A comprehensive survey of continual learning: Theory, method and application. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-short.39"},{"key":"e_1_3_2_1_41_1","volume-title":"Orthogonal Subspace Learning for Language Model Continual Learning. In The 2023 Conference on Empirical Methods in Natural Language Processing.","author":"Wang Xiao","unstructured":"Xiao Wang, Tianze Chen, Qiming Ge, Han Xia, Rong Bao, Rui Zheng, Qi Zhang, Tao Gui, and Xuanjing Huang. [n.d.]. Orthogonal Subspace Learning for Language Model Continual Learning. In The 2023 Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_1_42_1","volume-title":"Inscl: A data-efficient continual learning paradigm for fine-tuning large language models with instructions. arXiv preprint arXiv:2403.11435","author":"Wang Yifan","year":"2024","unstructured":"Yifan Wang, Yafei Liu, Chufan Shi, Haoling Li, Chen Chen, Haonan Lu, and Yujiu Yang. 2024b. Inscl: A data-efficient continual learning paradigm for fine-tuning large language models with instructions. arXiv preprint arXiv:2403.11435 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539439"},{"key":"e_1_3_2_1_44_1","volume-title":"Continual learning for large language models: A survey. arXiv preprint arXiv:2402.01364","author":"Wu Tongtong","year":"2024","unstructured":"Tongtong Wu, Linhao Luo, Yuan-Fang Li, Shirui Pan, Thuy-Trang Vu, and Gholamreza Haffari. 2024a. Continual learning for large language models: A survey. arXiv preprint arXiv:2402.01364 (2024)."},{"key":"e_1_3_2_1_45_1","volume-title":"Meta-rewarding language models: Self-improving alignment with llm-as-a-meta-judge. arXiv preprint arXiv:2407.19594","author":"Wu Tianhao","year":"2024","unstructured":"Tianhao Wu, Weizhe Yuan, Olga Golovneva, Jing Xu, Yuandong Tian, Jiantao Jiao, Jason Weston, and Sainbayar Sukhbaatar. 2024b. Meta-rewarding language models: Self-improving alignment with llm-as-a-meta-judge. arXiv preprint arXiv:2407.19594 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"From human memory to ai memory: A survey on memory mechanisms in the era of llms. arXiv preprint arXiv:2504.15965","author":"Wu Yaxiong","year":"2025","unstructured":"Yaxiong Wu, Sheng Liang, Chen Zhang, Yichao Wang, Yongyue Zhang, Huifeng Guo, Ruiming Tang, and Yong Liu. 2025. From human memory to ai memory: A survey on memory mechanisms in the era of llms. arXiv preprint arXiv:2504.15965 (2025)."},{"key":"e_1_3_2_1_47_1","volume-title":"PEToolLLM: Towards Personalized Tool Learning in Large Language Models. arXiv preprint arXiv:2502.18980","author":"Xu Qiancheng","year":"2025","unstructured":"Qiancheng Xu, Yongqi Li, Heming Xia, Fan Liu, Min Yang, and Wenjie Li. 2025. PEToolLLM: Towards Personalized Tool Learning in Large Language Models. arXiv preprint arXiv:2502.18980 (2025)."},{"key":"e_1_3_2_1_48_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Zhang Han","year":"2024","unstructured":"Han Zhang, Yu Lei, Lin Gui, Min Yang, Yulan He, Hui Wang, and Ruifeng Xu. 2024. Cppo: Continual learning for reinforcement learning with human feedback. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3716629"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:20:31Z","timestamp":1775838031000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792798"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":49,"alternative-id":["10.1145\/3774904.3792798","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792798","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}