Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt Optimization

ArXi:2605.30227v1 Announce Type: cross While Multi-Agent Systems (MAS) empower Large Language Models to tackle complex reasoning tasks through collaborative interaction, optimizing their dynamics remains a formidable challenge due to the discrete, non-differentiable nature of the computation graph and the sparsity of global supervisory signals. Existing black-box optimizers struggle to attribute trajectory-level failure to specific local components, resulting in inefficient, high-variance exploration.