Proposes 'Nomad', an exploration-first agent architecture that autonomously discovers insights in data without being limited by human prompts or questions.
April 1, 2026
Original Paper
Nomad: Autonomous Exploration and Discovery
arXiv · 2603.29353
The Takeaway
Most current agentic systems (like RAG) are reactive and rely on user-provided questions. Nomad uses an explicit 'Exploration Map' to proactively identify research directions and hypotheses, shifting the paradigm from 'Search' to 'Discovery' in large document corpora.
From the abstract
We introduce Nomad, a system for autonomous data exploration and insight discovery. Given a corpus of documents, databases, or other data sources, users rarely know the full set of questions, hypotheses, or connections that could be explored. As a result, query-driven question answering and prompt-driven deep-research systems remain limited by human framing and often fail to cover the broader insight space.Nomad addresses this problem with an exploration-first architecture. It constructs an expl