Nomad: Autonomous Exploration and Discovery
Bokang Jia, Samta Kamboj, Satheesh Katipomu, Seung Hun Han, Neha Sengupta, Andrew Jackson

TL;DR
Nomad is an autonomous exploration system that systematically investigates data sources to generate trustworthy, diverse insights and reports, surpassing traditional question-driven methods.
Contribution
It introduces an exploration-first architecture with an explicit Exploration Map and a comprehensive evaluation framework for autonomous discovery systems.
Findings
Nomad produces more trustworthy reports than baselines.
It generates higher-quality insights and more diversity.
Nomad outperforms in producing comprehensive, unbiased reports.
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 explicit Exploration Map over the domain and systematically traverses it to balance breadth and depth. It generates and selects hypotheses and investigates them with an explorer agent that can use document search, web search, and database tools. Candidate insights are then checked by an independent verifier before entering a reporting pipeline that produces cited reports and higher-level…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
