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

arXiv: https://arxiv.org/abs/2507.07257 · HTML: https://mlsanity.com/paper/2507.07257/

## 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.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 9 of 9)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Lightning-Fast Gravitational Wave Parameter Inference through Neural Amortization](https://mlsanity.com/paper/2010.12931/) (2020)
- [The AI Cosmologist I: An Agentic System for Automated Data Analysis](https://mlsanity.com/paper/2504.03424/) (2025)
- [Learned harmonic mean estimation of the Bayesian evidence with normalizing flows](https://mlsanity.com/paper/2405.05969/) (2024)
- [Neural Networks Optimized by Genetic Algorithms in Cosmology](https://mlsanity.com/paper/2209.02685/) (2022)
- [One-dimensional Convolutional Neural Networks for Detecting Transiting Exoplanets](https://mlsanity.com/paper/2312.07161/) (2023)
- [Constructing Impactful Machine Learning Research for Astronomy: Best Practices for Researchers and Reviewers](https://mlsanity.com/paper/2310.12528/) (2023)
- [Deep Learning and genetic algorithms for cosmological Bayesian inference speed-up](https://mlsanity.com/paper/2405.03293/) (2024)

## Built on by (most cited first, 8 of 8)

- [Agentic Exploration of Physics Models](https://mlsanity.com/paper/2509.24978/) (2025)
- [CLAPP: The CLASS LLM Agent for Pair Programming](https://mlsanity.com/paper/2508.05728/) (2025)
- [Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI](https://mlsanity.com/paper/2510.04978/) (2025)
- [Enhancing Agentic Autonomous Scientific Discovery with Vision-Language Model Capabilities](https://mlsanity.com/paper/2511.14631/) (2025)
- [DeepInflation: an AI agent for research and model discovery of inflation](https://mlsanity.com/paper/2601.14288/) (2026)
- [Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows](https://mlsanity.com/paper/2604.25345/) (2026)
- [Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves](https://mlsanity.com/paper/2605.11280/) (2026)
- [Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches](https://mlsanity.com/paper/2606.01145/) (2026)

## 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.