AI RESEARCH
AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle
arXiv CS.AI
•
ArXi:2605.31468v1 Announce Type: new Scientific research has traditionally been human-intensive, requiring researchers to coordinate literature, ideas, experiments, manuscripts, and review responses across long project cycles. The rise of LLM-based scientific agents creates an opportunity to automate this process. Such a system must the full research lifecycle, maintain structured persistent memory across projects, and improve its own research procedures over time.