Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912476932603904 |
|---|---|
| author | Xu, Licong Sarkar, Milind Lonappan, Anto I. Zubeldia, Íñigo Villanueva-Domingo, Pablo Casas, Santiago Fidler, Christian Amancharla, Chetana Tiwari, Ujjwal Bayer, Adrian Ekioui, Chadi Ait Cranmer, Miles Dimitrov, Adrian Fergusson, James Gandhi, Kahaan Krippendorf, Sven Laverick, Andrew Lesgourgues, Julien Lewis, Antony Meier, Thomas Sherwin, Blake Surrao, Kristen Villaescusa-Navarro, Francisco Wang, Chi Xu, Xueqing Bolliet, Boris |
| author_facet | Xu, Licong Sarkar, Milind Lonappan, Anto I. Zubeldia, Íñigo Villanueva-Domingo, Pablo Casas, Santiago Fidler, Christian Amancharla, Chetana Tiwari, Ujjwal Bayer, Adrian Ekioui, Chadi Ait Cranmer, Miles Dimitrov, Adrian Fergusson, James Gandhi, Kahaan Krippendorf, Sven Laverick, Andrew Lesgourgues, Julien Lewis, Antony Meier, Thomas Sherwin, Blake Surrao, Kristen Villaescusa-Navarro, Francisco Wang, Chi Xu, Xueqing Bolliet, Boris |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07257 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery Xu, Licong Sarkar, Milind Lonappan, Anto I. Zubeldia, Íñigo Villanueva-Domingo, Pablo Casas, Santiago Fidler, Christian Amancharla, Chetana Tiwari, Ujjwal Bayer, Adrian Ekioui, Chadi Ait Cranmer, Miles Dimitrov, Adrian Fergusson, James Gandhi, Kahaan Krippendorf, Sven Laverick, Andrew Lesgourgues, Julien Lewis, Antony Meier, Thomas Sherwin, Blake Surrao, Kristen Villaescusa-Navarro, Francisco Wang, Chi Xu, Xueqing Bolliet, Boris Artificial Intelligence Instrumentation and Methods for Astrophysics Computation and Language Multiagent Systems 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. |
| title | Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery |
| topic | Artificial Intelligence Instrumentation and Methods for Astrophysics Computation and Language Multiagent Systems |
| url | https://arxiv.org/abs/2507.07257 |