一作ACL 2026Findings· Findings of ACL
Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization
Shan He · Runze Wang · Zhuoyun Du · Huiyu Bai · Zouying Cao · Yu Cheng · Zerui Huang (Taobao &
摘要
Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of “Agent Engineering.” Existing automatic optimization methods, primarily focused on flat prompt tuning, lack the structural awareness to debug the intricate web of interactions in MAS. More critically, thes...