URSA: The Universal Research and Scientific Agent

Michael Grosskopf, Russell Bent, Rahul Somasundaram, Isaac Michaud, Arthur Lui +2 more
6/27/2025
cs.AI

No official code found. Best implementation: lanl/ursa (71 stars, last commit 2026-04-30).

Abstract

Large language models (LLMs) have moved far beyond their initial form as simple chatbots, now carrying out complex reasoning, planning, writing, coding, and research tasks. These skills overlap significantly with those that human scientists use day-to-day to solve complex problems that drive the cutting edge of research. Using LLMs in "agentic" AI has the potential to revolutionize modern science and remove bottlenecks to progress. In this work, we present URSA, a scientific agent ecosystem for accelerating research tasks. URSA consists of a set of modular agents and tools, including coupling to advanced physics simulation codes, that can be combined to address scientific problems of varied complexity and impact. This work highlights the architecture of URSA, as well as examples that highlight the potential of the system.

View on arXivView PDF

Code Implementations(1)

lanl/ursaCommunity71%

Universal Research and Scientific Agent

7135Just, PythonAug 15, 20255 months agoNOASSERTION

Similar Papers

CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution

90% match2025

LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities

88% match2024

LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research

87% match1 repo102025

SciSciGPT: Advancing Human-AI Collaboration in the Science of Science

87% match2025

Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science

87% match2026

Can Theoretical Physics Research Benefit from Language Agents?

86% match2025

Cite this paper

@article{grosskopf2025ursa,
  title  = {URSA: The Universal Research and Scientific Agent},
  author = {Michael Grosskopf and Russell Bent and Rahul Somasundaram and Isaac Michaud and Arthur Lui and Nathan Debardeleben and Earl Lawrence},
  year   = {2025},
  eprint = {2506.22653},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2506.22653v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2506.22653.svg)](https://codeofpaper.com/paper/2506.22653)

Discussion