一作ACL 2026Findings· Findings of ACL
Evolving Agentic Workflow Driven by Human-Agent Collaboration
Yuxin Liu · Jinxuan Zhang · Yuezhang Peng · Hefeng Zhou · Xiangfeng Wang · Jiong Lou · Chentao Wu · Jie Li · Jingjing Qu · Chaochao Lu
摘要
Agentic workflows, composed of multiple collaborating Large Language Models (LLMs), have become a key paradigm for complex problem-solving. However, their effectiveness is often hindered by three critical challenges: high manual design costs, inefficient agentic search, and poor dynamic adaptabil...