Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery
This addresses the problem of automating complex scientific discovery workflows for researchers, representing a novel application rather than an incremental improvement.
The researchers developed an autonomous multi-agent system called cmbagent that uses about 30 specialized LLM agents with a Planning & Control strategy to automate scientific research tasks without human intervention, successfully applying it to a PhD-level cosmology task where it achieved superior performance over state-of-the-art LLMs on benchmark sets.
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.