Socialized Coevolution: Advancing a Better World through Cross-Task Collaboration

Xinjie Yao, Yu Wang, Pengfei Zhu, Wanyu Lin, Ruipu Zhao, Zhoupeng Guo, Weihao Li, Qinghua Hu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71780-71797, 2025.

Abstract

Traditional machine societies rely on data-driven learning, overlooking interactions and limiting knowledge acquisition from model interplay. To address these issues, we revisit the development of machine societies by drawing inspiration from the evolutionary processes of human societies. Motivated by Social Learning (SL), this paper introduces a practical paradigm of Socialized Coevolution (SC). Compared to most existing methods focused on knowledge distillation and multi-task learning, our work addresses a more challenging problem: not only enhancing the capacity to solve new downstream tasks but also improving the performance of existing tasks through inter-model interactions. Inspired by cognitive science, we propose Dynamic Information Socialized Collaboration (DISC), which achieves SC through interactions between models specialized in different downstream tasks. Specifically, we introduce the dynamic hierarchical collaboration and dynamic selective collaboration modules to enable dynamic and effective interactions among models, allowing them to acquire knowledge from these interactions. Finally, we explore potential future applications of combining SL and SC, discuss open questions, and propose directions for future research, aiming to spark interest in this emerging and exciting interdisciplinary field. Our code will be publicly available at https://github.com/yxjdarren/SC.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-yao25e, title = {Socialized Coevolution: Advancing a Better World through Cross-Task Collaboration}, author = {Yao, Xinjie and Wang, Yu and Zhu, Pengfei and Lin, Wanyu and Zhao, Ruipu and Guo, Zhoupeng and Li, Weihao and Hu, Qinghua}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {71780--71797}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/yao25e/yao25e.pdf}, url = {https://proceedings.mlr.press/v267/yao25e.html}, abstract = {Traditional machine societies rely on data-driven learning, overlooking interactions and limiting knowledge acquisition from model interplay. To address these issues, we revisit the development of machine societies by drawing inspiration from the evolutionary processes of human societies. Motivated by Social Learning (SL), this paper introduces a practical paradigm of Socialized Coevolution (SC). Compared to most existing methods focused on knowledge distillation and multi-task learning, our work addresses a more challenging problem: not only enhancing the capacity to solve new downstream tasks but also improving the performance of existing tasks through inter-model interactions. Inspired by cognitive science, we propose Dynamic Information Socialized Collaboration (DISC), which achieves SC through interactions between models specialized in different downstream tasks. Specifically, we introduce the dynamic hierarchical collaboration and dynamic selective collaboration modules to enable dynamic and effective interactions among models, allowing them to acquire knowledge from these interactions. Finally, we explore potential future applications of combining SL and SC, discuss open questions, and propose directions for future research, aiming to spark interest in this emerging and exciting interdisciplinary field. Our code will be publicly available at https://github.com/yxjdarren/SC.} }
Endnote
%0 Conference Paper %T Socialized Coevolution: Advancing a Better World through Cross-Task Collaboration %A Xinjie Yao %A Yu Wang %A Pengfei Zhu %A Wanyu Lin %A Ruipu Zhao %A Zhoupeng Guo %A Weihao Li %A Qinghua Hu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-yao25e %I PMLR %P 71780--71797 %U https://proceedings.mlr.press/v267/yao25e.html %V 267 %X Traditional machine societies rely on data-driven learning, overlooking interactions and limiting knowledge acquisition from model interplay. To address these issues, we revisit the development of machine societies by drawing inspiration from the evolutionary processes of human societies. Motivated by Social Learning (SL), this paper introduces a practical paradigm of Socialized Coevolution (SC). Compared to most existing methods focused on knowledge distillation and multi-task learning, our work addresses a more challenging problem: not only enhancing the capacity to solve new downstream tasks but also improving the performance of existing tasks through inter-model interactions. Inspired by cognitive science, we propose Dynamic Information Socialized Collaboration (DISC), which achieves SC through interactions between models specialized in different downstream tasks. Specifically, we introduce the dynamic hierarchical collaboration and dynamic selective collaboration modules to enable dynamic and effective interactions among models, allowing them to acquire knowledge from these interactions. Finally, we explore potential future applications of combining SL and SC, discuss open questions, and propose directions for future research, aiming to spark interest in this emerging and exciting interdisciplinary field. Our code will be publicly available at https://github.com/yxjdarren/SC.
APA
Yao, X., Wang, Y., Zhu, P., Lin, W., Zhao, R., Guo, Z., Li, W. & Hu, Q.. (2025). Socialized Coevolution: Advancing a Better World through Cross-Task Collaboration. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:71780-71797 Available from https://proceedings.mlr.press/v267/yao25e.html.

Related Material