Martin Legrand, Tao Jiang, Matthieu Feraud, Benjamin Navet, Yousouf Taghzouti,
Fabien Gandon, Elise Dumont, Louis-Félix Nothias
Current Autonomous Scientific Research (ASR) systems, despite leveraging large language models (LLMs)
and agentic architectures, remain constrained by fixed workflows and toolsets that prevent adaptation
to evolving tasks and environments. We introduce Mimosa, an evolving multi-agent framework
that automatically synthesizes task-specific multi-agent workflows and iteratively refines them through
experimental feedback. Mimosa leverages the Model Context Protocol (MCP) for dynamic tool discovery,
generates workflow topologies via a meta-orchestrator, executes subtasks through code-generating agents
that invoke available tools and scientific software libraries, and scores executions with an LLM-based
judge whose feedback drives workflow refinement.
Madina Bekbergenova, Lucas Pradi, Benjamin Navet, Emma Tysinger, Matthieu Feraud,
Yousouf Taghzouti, Martin Legrand, Tao Jiang, Franck Michel, Yan Zhou Chen,
Soha Hassoun, Olivier Kirchhoffer, Jean-Luc Wolfender, Florence Mehl, Marco Pagni,
Wout Bittremieux, Fabien Gandon, Louis-Félix Nothias
Mass spectrometry metabolomics generates vast amounts of data requiring advanced methods for
interpretation. Knowledge graphs address these challenges by structuring mass spectrometry data,
metabolite information, and their relationships into a connected network. However, effective use
of a knowledge graph demands an in-depth understanding of its ontology and query language syntax.
To overcome this, we designed MetaboT, an AI system utilizing large language models (LLMs)
to translate user questions into SPARQL semantic query language for operating on knowledge graphs.
We demonstrate its effectiveness using the Experimental Natural Products Knowledge Graph (ENPKG),
a large-scale public knowledge graph for plant natural products.