NORA: A Harness-Engineered Autonomous Research Agent for End-to-End Spatial Data Science
- URL: http://arxiv.org/abs/2605.02092v1
- Date: Sun, 03 May 2026 23:22:01 GMT
- Title: NORA: A Harness-Engineered Autonomous Research Agent for End-to-End Spatial Data Science
- Abstract summary: This paper introduces NORA (Night Owl Research Agent), a multi-agent autonomous research system purpose-built for GIScience and spatial data science.<n> NORA orchestrates the complete research lifecycle through a skills-first architecture comprising 21 domain-specialized workflow skills, 9 specialist sub-agents, and custom Model Context Protocol (MCP) servers.<n>We formalize the authoritative concept of harness engineering for scientific research agents, demonstrating how lifecycle hooks, safety gates, generator-evaluator separation, human-in-the-loop, and state persistence ensure reliable and reproducible autonomous research.
- Score: 13.671260946635813
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: The automation of scientific research workflows has emerged as a transformative frontier in artificial intelligence, yet existing autonomous research agents remain largely domain-agnostic, lacking the specialized reasoning, method selection, and data acquisition capabilities required for rigorous spatial data science. This paper introduces NORA (Night Owl Research Agent), a harness-engineered, multi-agent autonomous research system purpose-built for GIScience and spatial data science. NORA orchestrates the complete research lifecycle through a skills-first architecture comprising 21 domain-specialized workflow skills, 9 specialist sub-agents, and custom Model Context Protocol (MCP) servers. Central to the system's design are two novel domain-specialized skills: a spatial analysis skill unit that encodes decision frameworks for exploratory spatial data analysis, spatial regression, and diagnostics; and a spatial data download skill that supports reproducible acquisition from authoritative geospatial data sources. We formalize the concept of harness engineering for scientific research agents, demonstrating how lifecycle hooks, safety gates, generator-evaluator separation, human-in-the-loop, and state persistence ensure reliable and reproducible autonomous research. We evaluate NORA through case studies by 6 domain specialists and 3 LLM reviewers across seven dimensions (novelty, quality, rigor, etc). Results demonstrate that domain-specialized harness engineering substantially improves the efficiency and quality of research output compared to general-purpose agent configurations.
Related papers
- Benchmarking AI Agents for Addressing Scientific Challenges Across Scales [118.2204632627895]
SciAgentArena is a systematic benchmark for evaluating AI agents in real-world scientific research scenarios.<n>It comprises approximately 200 tasks with stepwise verification and an interactive, agent-agnostic environment for assessing diverse AI agents.<n>We find that current agents can contribute effectively to well-specified data-analysis, particularly when the task structure and evaluation criteria are clear.
arXiv Detail & Related papers (2026-06-10T22:55:30Z) - SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning [54.194672921128785]
We introduce SciResearcher, a fully automated agentic framework for frontier-science data construction.<n>SciResearcher synthesizes diverse conceptual and computational tasks grounded in academic evidence.<n>We develop SciResearcher-8B, an agent foundation model that achieves 19.46% on the HLE-Bio/Chem-Gold benchmark.
arXiv Detail & Related papers (2026-05-02T15:26:45Z) - AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery [55.70879973230979]
AutoResearchBench is a benchmark for autonomous scientific literature discovery.<n>Compared to previous benchmarks on agentic web browsing, AutoResearchBench is research-oriented.<n>Even the most powerful LLMs, despite having largely conquered general agentic web-browsing benchmarks such as BrowseComp, achieve only 9.39% accuracy on Deep Research and 9.31% IoU on Wide Research.
arXiv Detail & Related papers (2026-04-28T06:05:17Z) - ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers? [29.17900668495058]
We introduce ReplicationBench, an evaluation framework for frontier AI agents.<n>It tests whether agents can replicate entire research papers drawn from the astrophysics literature.<n>R ReplicationBench establishes the first benchmark of paper-scale, expert-validated astrophysics research tasks.
arXiv Detail & Related papers (2025-10-28T16:21:19Z) - A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers [251.23085679210206]
Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research.<n>This survey reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate.<n>We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge.
arXiv Detail & Related papers (2025-08-28T18:30:52Z) - From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery [108.1082357960201]
Agentic AI shows capabilities in hypothesis generation, experimental design, execution, analysis, and iterative refinement.<n>This survey provides a domain-oriented review of autonomous scientific discovery across life sciences, chemistry, materials science, and physics.
arXiv Detail & Related papers (2025-08-18T05:25:54Z) - From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery [67.07598263346591]
Large Language Models (LLMs) are catalyzing a paradigm shift in scientific discovery.<n>This survey systematically charts this burgeoning field, placing a central focus on the changing roles and escalating capabilities of LLMs in science.
arXiv Detail & Related papers (2025-05-19T15:41:32Z) - INDUS: Effective and Efficient Language Models for Scientific Applications [8.653859684720231]
Large language models (LLMs) trained on general domain corpora showed remarkable results on natural language processing (NLP) tasks.
We developed INDUS, a comprehensive suite of LLMs tailored for the closely-related domains of Earth science, biology, physics, heliophysics, planetary sciences and astrophysics.
We show that our models outperform both general-purpose (RoBERTa) and domain-specific (SCIBERT) encoders on new tasks as well as existing tasks in the domains of interest.
arXiv Detail & Related papers (2024-05-17T12:15:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.