Article

Competing with AI Scientists: Agent-Driven Approach to Astrophysics Research

2026-03-25

Abstract excerpt

<title>Abstract</title> We present an agent-driven approach to the construction of parameter inference pipelines for scientific data analysis. Our method leverages a multi-agent system, Cmbagent 1 (the analysis system of the AI scientist Denario 2 ), in which specialized agents collaborate to generate research ideas, write and execute code, evaluate results, and iteratively refine t...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: d559889c-8ebd-53f4-b59b-00ae25257be0
DOI: 10.21203/rs.3.rs-9114794/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 8 closest

Competing with AI Scientists: Agent-Driven Approach to Astrophysics ResearchDOI 10.21203/rs.3.rs-9114794/v1Read

The AI Cosmologist I: An Agentic System for Automated Data AnalysisSemantic proximity Read

A Self-Evolving AI Agent System Accelerating the Understanding of Climate Change and VariabilitySemantic proximity Read

StarWhisper Telescope: Agent-Based Observation Assistant System to Approach AI AstrophysicistSemantic proximity Read

PhysAgent: A Multi-Agent Approach to the Automated Discovery of Physical LawsSemantic proximity Read

Autonomous Scientific Discovery Through Hierarchical AI Scientist SystemsSemantic proximity Read

Galaxy Circus: A New Paradigm for Anomalous Galaxy Discovery with Artificial Intelligence and Citizen ScienceSemantic proximity Read

Agentic Laboratories of the Future: Towards World Models for Scientific DiscoverySemantic proximity Read

A Coherence-Based Framework for Backward Reconstruction of Solar System HistoriesSemantic proximity Read