Skip to main content

TL;DR

  • synth-large model now available in Research Agent harness for MIPRO optimization
  • Improved MIPRO and GEPA visualizations in the dashboard

synth-large for Research Agents

Research Agents can now use synth-large as the agent model for MIPRO-based prompt optimization. Configure via the model dropdown in the Research Agent job settings.

MIPRO & GEPA Visualization Improvements

Updated dashboard components for both optimization algorithms:
  • MIPRO: Better progress tracking for candidate evaluation and refinement stages
  • GEPA: Clearer display of population evolution and mutation patterns across generations