iiinova — where your digital self keeps evolving

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 23/06/2026

The source corpus builds on the computational-metabolomics review series started by @biswamisra.bsky.social (2014) @jjjvanderhooft.bsky.social , now maintained by Enveda — thanks to Tobias Kind for great team work in Dagstuhl. 11/

131

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 23/06/2026

My take-home: the bottleneck left is not technical — it's collective. The community must validate, curate & govern these benchmarks and skills transparently, so science, not the vendor, stays in control. Try it, break it, join us and contribute to the upcoming community paper. 10/

100

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 23/06/2026

👉 The release: the first ASB Skill Collection for metabolomics. 🔹 5,865 skills · 909 tools · 568 papers 🔹 LC-MS/MS + GC-MS, MS-imaging, ion mobility, lipidomics, NMR 🔹 evidence-grounded, EDAM-annotated, open (CC-BY-4.0) 8/

121

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 23/06/2026

So as a community effort started at Dagstuhl, we built the AgenticScienceBuilder (ASB): a pipeline that reads real method papers and distills them into benchmark tasks, skills & tools — each verified against its source. 7/

100

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 23/06/2026

But is an agent good at our science? That question was sharpened at the Dagstuhl Seminar on Computational Metabolomics (April 2026). The bottleneck: no metabolomics benchmark, no domain skills/grounding. 6/

110

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 23/06/2026

Step 3: keep agents honest. Perspicacité grounds them in the literature — an open, local-first literature-RAG engine where the evidence is yours and traceable, not a black box. github.com/HolobiomicsL... 5/

110

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 23/06/2026

The community has the ability and tools for producing metabolomics data at scale — a single plant/microbe collection can hold 10,000+ extracts and millions of spectra. We're not yet as good at asking it everything we could. The answer lives across spectra, taxa, annotations & assays at once. 2/

110

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 23/06/2026

Today at #MetSoc2026 I gave a keynote presentation on self-evolving, multi-agent AI for metabolomics — from @holobiomicslab.bsky.social. The headline outcome: we're releasing the first ASB Skill Collection — open, evidence-grounded metabolomics building blocks for any scientific AI agents. 🧵👇

194

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 04/05/2026

I love the photos were the colleagues are checking out the preliminary results of the prototype for the benchmark pipeline on my computer (the one with a CNRS sticker!) during one legendary "beer session".

031

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 04/05/2026

At the same time, this was very important to have discussions with colleagues on the short/long-term challenges/risks. There are many and we should anticipate.

000

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 04/05/2026

... like Mimosa-AI (arxiv.org/abs/2603.28986) and those from MetaboLinkAI More generally, I was pleased to notice the general interest in agentic-AI and admission of its transformative potential for metabolomics and science - which wasn't that widely recognized 2 years ago.

arxiv.org

Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research

Current Autonomous Scientific Research (ASR) systems, despite leveraging large language models (LLMs) and agentic architectures, remain constrained by fixed workflows and toolsets that prevent adaptat...

110

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 04/05/2026

The first sessions on AI converged to the existing gap, and that follow-up session enabled some powerful brainstorming with participants. We are now crafting an aligned benchmark that will help in designing and evaluating emerging agentic AI systems for metabolomics, ...

100

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 04/05/2026

This time, in addition to act as a notetaker for several sessions, I co-moderated, with Florian Huber and Tobias Kind, a session on "Benchmarking tasks/workflows for metabolomics agent systems" on 29th April 2026.

100

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 04/05/2026

... meeting old and new friends. I am so grateful to be part of seminar (again), which truly shaped our community and research direction over the year.

100

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 04/05/2026

Thanks and congratulations to @jjjvanderhooft.bsky.social, Soha Hassoun @pluskal-lab.org, Stacey Reinke for organizing this landmark #Dagstuhl Computational Metabolomics seminar 26181 ! www.dagstuhl.de/en/seminars/... What an amazing four days with many fruitful discussions and interactions ...

131

Reposted by Louis-Felix Nothias - HolobiomicsLab

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 02/04/2026

We've been building multi-agent AI for science at @holobiomicslab.bsky.social. We just released Mimosa (preprint, 30 March 2026) — a framework where the multi-agent workflows themselves evolve instead of following a fixed recipe. arxiv.org/abs/2603.28986

163

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 02/04/2026

Next steps for Mimosa: – Population-based workflow exploration – Domain-specific skill acquisition from published methods – Persistent failure-aware memory – Evaluation on lightweight open-source models Goal: a community-extensible engine for autonomous scientific AI.

100

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 02/04/2026

Why does academia need to build its own AI tools? If we stop building because big tech is ahead, we lose the skills and infrastructure to govern the tools research will depend on. Openness isn't just principle — it's how science retains its sovereignty.

110

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 02/04/2026

Everything is saved: every workflow topology, every agent prompt, every intermediate file. Tools run in containerized MCP servers — environment frozen, dependencies locked. A Python script can replay any step. Fully logged. Auditable. Replayable.

100

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 02/04/2026

On ScienceAgentBench (102 real scientific tasks, 4 disciplines): – Single agent: 38.2% – Static multi-agent: 32.4% – Iterative learning: 43.1% Tested across bioinformatics, computational chemistry, GIS, and cognitive neuroscience.

110

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 02/04/2026

A meta-orchestrator decomposes a problem into coordinated agent roles. Agents discover tools at runtime via MCP (Model Context Protocol). An LLM judge evaluates results and drives workflow evolution. The topology itself is what evolves — not just the outputs.

110

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 02/04/2026

Most AI systems for science follow fixed pipelines. But research is non-linear — you screen, dock, simulate, realize your assumptions were wrong, and restart. Fixed architectures can't adapt. Mimosa was built to change that.

120

Louis-Felix Nothias - HolobiomicsLab @holobiomicslab.bsky.social · 02/04/2026

163