mlsanityData to 14 Oct 2026

Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery

arXiv 2507.07257 ↗First posted 9 Jul 2025cs.AI astro-ph.IM cs.CLcited by 8

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

We present a multi-agent system for automation of scientific research tasks, cmbagent (https://github.com/CMBAgents/cmbagent). The system is formed by about 30 Large Language Model (LLM) agents and implements a Planning & Control strategy to orchestrate the agentic workflow, with no human-in-the-loop at any point. Each agent specializes in a different task (performing retrieval on scientific papers and codebases, writing code, interpreting results, critiquing the output of other agents) and the system is able to execute code locally. We successfully apply cmbagent to carry out a PhD level cosmology task (the measurement of cosmological parameters using supernova data) and evaluate its performance on two benchmark sets, finding superior performance over state-of-the-art LLMs. The source code is available on GitHub, demonstration videos are also available, and the system is deployed on HuggingFace and will be available on the cloud.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 9 of its 63 references that are in the map. First posted on arXiv 9 Jul 2025.

Builds on

9 of 63 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025The AI Cosmologist I: An Agentic System for Automated Data Analysis4 Apr

Other references · 8

  1. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  2. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  3. 2020Lightning-Fast Gravitational Wave Parameter Inference through Neural Amortizationcited by 17
  4. 2024Learned harmonic mean estimation of the Bayesian evidence with normalizing flowscited by 7
  5. 2022Neural Networks Optimized by Genetic Algorithms in Cosmologycited by 4
  6. 2023One-dimensional Convolutional Neural Networks for Detecting Transiting Exoplanetscited by 3
  7. 2023Constructing Impactful Machine Learning Research for Astronomy: Best Practices for Researchers and Reviewerscited by 1
  8. 2024Deep Learning and genetic algorithms for cosmological Bayesian inference speed-upcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2025Agentic Exploration of Physics Modelscited by 6
  2. 2025CLAPP: The CLASS LLM Agent for Pair Programmingcited by 3
  3. 2025Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AIcited by 3
  4. 2025Enhancing Agentic Autonomous Scientific Discovery with Vision-Language Model Capabilitiescited by 2
  5. 2026DeepInflation: an AI agent for research and model discovery of inflationcited by 1
  6. 2026Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflowscited by 1
  7. 2026Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Wavescited by 1
  8. 2026Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branchescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology
  2. 2026Competing with AI Scientists: Agent-Driven Approach to Astrophysics Research
  3. 2025Bridging Literature and the Universe Via A Multi-Agent Large Language Model System
  4. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
  5. 2025ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows
  6. 2025Kosmos: An AI Scientist for Autonomous Discovery
  7. 2026A Cloud-based Multi-Agentic Workflow for Science
  8. 2025Evaluating Retrieval-Augmented Generation Agents for Autonomous Scientific Discovery in Astrophysics