Moves automated research from stateless linear pipelines to a persistent Research World Model that maintains a self-correcting knowledge graph of gaps and methods.
March 26, 2026
Original Paper
AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model
arXiv · 2603.24402
The Takeaway
Instead of just generating papers, this framework treats research as a shared-memory exploration where agents verify each other's findings and identify module-level gaps. It represents a shift toward more 'agentic' scientific discovery that builds on its own previous insights.
From the abstract
Existing automated research systems operate as stateless, linear pipelines, generating outputs without maintaining a persistent understanding of the research landscape. They process papers sequentially, propose ideas without structured gap analysis, and lack mechanisms for agents to verify or refine each other's findings. We present AutoProf (Autonomous Professor), a multi-agent orchestration framework where specialized agents provide end-to-end AI research supervision driven by human interests,