AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
AgentGrad is proposed, a prompt optimization framework for multi-agent systems based on sequential intervention and semantic textual gradient abstraction that clusters semantically similar gradients to prevent mixing unrelated failure modes, and abstracts each cluster into a generalized gradient that captures the share...
Jaewon Chu, Jinwoo Seo, J. Cho et al.
· 1 citation