{"ID":2863330,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24323","arxiv_id":"2509.24323","title":"MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems","abstract":"The past two years have witnessed the meteoric rise of Large Language Model (LLM)-powered multi-agent systems (MAS), which harness collective intelligence and exhibit a remarkable trajectory toward self-evolution. This paradigm has rapidly progressed from manually engineered systems that require bespoke configuration of prompts, tools, roles, and communication protocols toward frameworks capable of automated orchestration. Yet, dominant automatic multi-agent systems, whether generated by external modules or a single LLM agent, largely adhere to a rigid ``\\textit{generate-once-and-deploy}'' paradigm, rendering the resulting systems brittle and ill-prepared for the dynamism and uncertainty of real-world environments. To transcend this limitation, we introduce MAS$^2$, a paradigm predicated on the principle of recursive self-generation: a multi-agent system that autonomously architects bespoke multi-agent systems for diverse problems. Technically, we devise a ``\\textit{generator-implementer-rectifier}'' tri-agent team capable of dynamically composing and adaptively rectifying a target agent system in response to real-time task demands. Collaborative Tree Optimization is proposed to train and specialize these meta-agents. Extensive evaluation across seven benchmarks reveals that MAS$^2$ achieves performance gains of up to $19.6\\%$ over state-of-the-art MAS in complex scenarios such as deep research and code generation. Moreover, MAS$^2$ exhibits superior cross-backbone generalization, effectively leveraging previously unseen LLMs to yield improvements of up to $15.1\\%$. Crucially, these gains are attained without incurring excessive token costs, as MAS$^2$ consistently resides on the Pareto frontier of cost-performance trade-offs. The source codes are available at https://github.com/yeyeyeah2/MAS2.","short_abstract":"The past two years have witnessed the meteoric rise of Large Language Model (LLM)-powered multi-agent systems (MAS), which harness collective intelligence and exhibit a remarkable trajectory toward self-evolution. This paradigm has rapidly progressed from manually engineered systems that require bespoke configuration o...","url_abs":"https://arxiv.org/abs/2509.24323","url_pdf":"https://arxiv.org/pdf/2509.24323v1","authors":"[\"Kun Wang\",\"Guibin Zhang\",\"ManKit Ye\",\"Xinyu Deng\",\"Dongxia Wang\",\"Xiaobin Hu\",\"Jinyang Guo\",\"Yang Liu\",\"Yufei Guo\"]","published":"2025-09-29T06:20:10Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":608997,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2863330,"paper_url":"https://arxiv.org/abs/2509.24323","paper_title":"MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems","repo_url":"https://github.com/yeyeyeah2/MAS2","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}