Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance

  • 类型:arxiv
  • 标识:2610.02396
  • 链接:https://arxiv.org/abs/2610.02396
  • 主分类:agent
  • 形态:method
  • TLDR:Multi-agent systems (MAS) built from large language models coordinate specialized agents to tackle complex tasks, but effective workflows are difficult to design in advance. Test-time evolution refines workflows using execution feedback, yet broad revisions can disturb useful components, while re-executing unchanged requests can incur redundant computation. Inspired by the interplay of inheritance and selection in biological evolution, we introduce Inherit-MAS, which makes inheritance explicit at the workflow and execution levels. A meta-model first synthesizes a workflow of worker agents with
  • 待LLM分类:否
  • 标题中文:Inherit-MAS:通过工作流与执行继承实现多 Agent 系统的测试时演化
  • TLDR中文:由大语言模型构建的多 Agent 系统 (MAS) 通过协调专业化 Agent 来处理复杂任务,但有效的工作流难以预先设计。测试时演化利用执行反馈来优化工作流,然而广泛的修订可能扰动有用组件,而重执行未变更的请求会带来冗余计算。受生物进化中继承与选择相互作用的启发,我们引入 Inherit-MAS,在工作流和执行层面显式化继承。元模型首先综合出由 worker Agent 组成的工作流
  • 来源文件:
  • /inbox/tom/_candidates/2026-10-09-agent-rag-longcontext-candidates.json