AI RESEARCH

RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgets

arXiv CS.AI

ArXi:2604.04347v1 Announce Type: new 2026 has brought an explosion of interest in LLM-guided evolution of agentic artifacts, with systems like GEPA and Autoresearch nstrating that LLMs can iteratively improve prompts, code, and agent architectures across diverse domains.