[2603.24402] AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model

Computer Science > Artificial Intelligence arXiv:2603.24402 (cs) [Submitted on 25 Mar 2026 (v1), last revised 26 Mar 2026 (this version, v2)] Title:AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model Authors:Yunbo Long View a PDF of the paper titled AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model, by Yunbo Long View PDF HTML (experimental) Abstract:Existing automated research systems operate as stateless, linear pipelines -- generating outputs without maintaining any persistent understanding of the research landscape they navigate. They process papers sequentially, propose ideas without structured gap analysis, and lack mechanisms for agents to verify, challenge, or refine each other's findings. We present \textbf{AI-Supervisor}, a multi-agent orchestration framework where specialized agents provide end-to-end AI research supervision driven by human interests -- from literature review through gap discovery, method development, evaluation, and paper writing -- through autonomous exploration and self-correcting updates of research knowledge. Unlike sequential pipelines, AI-Supervisor maintains a continuously evolving \emph{Research World Model}, implemented as a Knowledge Graph, that captures methods, benchmarks, known limitations, and unexplored gaps, serving as shared memory across all agents and enabling agents to explore and build upon a structured understanding of the research landscape. The fra...