04:00
2026-10-12
arxiv.org
ai-agents
Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting
Applying reflective prompt evolution (GEPA) to the two system prompts of a multi-agent deep-research agent raised held-out citation reward by 0.079, from 0.702 to 0.781, with a bootstrap 95% confidenc…