The reviewed record of science sign in
Pith

arxiv: 2507.07257 · v2 · pith:UA64EWLX · submitted 2025-07-09 · cs.AI · astro-ph.IM· cs.CL· cs.MA

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

Licong Xu , Milind Sarkar , Anto I. Lonappan , \'I\~nigo Zubeldia , Pablo Villanueva-Domingo , Santiago Casas , Christian Fidler , Chetana Amancharla
show 18 more authors
Ujjwal Tiwari Adrian Bayer Chadi Ait Ekioui Miles Cranmer Adrian Dimitrov James Fergusson Kahaan Gandhi Sven Krippendorf Andrew Laverick Julien Lesgourgues Antony Lewis Thomas Meier Blake Sherwin Kristen Surrao Francisco Villaescusa-Navarro Chi Wang Xueqing Xu Boris Bolliet
This is my paper

Reviewed by Pithpith:UA64EWLXopen to challenge →

classification cs.AI astro-ph.IMcs.CLcs.MA
keywords systemagentsavailablecmbagentcodescientificcontrolgithub
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows

    cs.AI 2026-04 unverdicted novelty 6.0

    Case study of CMBAgent on 18 astrophysical tasks finds strong performance on well-specified problems but frequent silent failures yielding physically inconsistent outputs.

  2. Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators

    cs.MA 2026-05 unverdicted novelty 5.0

    Sibyl-AutoResearch introduces self-evolving trial-and-error harnesses with auditable conversion units that link trial signals to updated research behaviors and harness repairs in autonomous systems.

  3. Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves

    gr-qc 2026-05 unverdicted novelty 5.0

    GWAgent agentic workflow produces analytic surrogates for eccentric BBH waveforms with 6.9e-4 median mismatch and 8.4x speedup, outperforming baselines, and infers eccentricity for GW200129.

  4. Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows

    cs.AI 2026-04 unverdicted novelty 4.0

    CMBAgent achieves high accuracy on well-specified astrophysical tasks with context but generates silent, plausible-yet-incorrect outputs on reasoning-challenging problems, with no self-diagnosis of inconsistencies.