Self-Evolving Multi-Agent Systems via Textual Backpropagation
Xiaowen Ma, Yunpu Ma, Chenyang Lin, Sikuan Yan, Jinhe Bi, Zixuan Cao, Yijun Tian, Volker Tresp, Hinrich Schuetze · 2026
Leveraging multiple Large Language Models (LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations.To overcome these constraints, we present the Agentic Neural Network (AN N ), a framework that conceptualizes multi-agent collaboration as a layered neural network architecture.In this design, each agent operates as a node, and each layer forms a cooperative team focused on a specific subtask.Agentic Neural Network follows a two-phase optimization strategy: (1) Forward Phase -Drawing inspiration from neural network forward passes, tasks are dynamically decomposed into subtasks, and cooperative agent teams with suitable aggregation methods are constructed layer by layer.(2) Backward Phase -Mirroring backpropagation, we refine both global and local collaboration through iterative feedback, allowing agents to self-evolve their roles, prompts, and coordination.This neuro-symbolic approach enables AN N to create new or specialized agent teams post-training, delivering notable gains in accuracy and adaptability.Across seven benchmark datasets, AN N surpasses leading multi-agent baselines under the same configurations, showing consistent performance improvements.