EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

ArXi:2603.08127v1 Announce Type: new The increasing adoption of Large Language Models (LLMs) has enabled AI scientists to perform complex end-to-end scientific discovery tasks requiring coordination of specialized roles, including idea generation and experimental execution. However, most state-of-the-art AI scientist systems rely on static, hand-designed pipelines and fail to adapt based on accumulated interaction histories. As a result, these systems overlook promising research directions, repeat failed experiments, and pursue infeasible ideas. To address this, we