MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems

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 multiagent systems, whether generated by external modules or a single LLM agent, largely adhere to a rigid "generate-once-and-deploy" paradigm, rendering the resulting systems brittle and ill-prepared for the dynamism and uncertainty of realworld 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 "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 .