作者位次 #3/9ACL 2026Findings· Findings of ACL
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
摘要
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 ( \mathcal{ANN} )...