MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic Models
Josh LoeckeriD, Narayana Pujara, William Bryant, Bhanwar Lal PuniyaiD, Prakash PackrisamyiD, Ahmed Abdeen HamediD, Tomáš HelikariD
Abstract
LLM agents are increasingly used for scientific reasoning, but their fluent-sounding outputs can diverge from verifiable computational evidence, limiting their reliability for biomedical hypothesis generation. We developed MechAInistic, a multi-agent system in which an independently configured Reviewer agent supervises a planning Architect agent at each stage of the workflow, with all reasoning grounded in executable mechanistic-model analyses rather than language-model text alone. The Reviewer scores plans and intermediate results against pre-specified rubrics and triggers re-planning or re-execution when scores fall below threshold, producing an auditable chain from a natural-language question to model-derived evidence and cited literature. We instantiate the system over paired constraint-based metabolic models using COBRApy, supporting pathway comparison, perturbation analysis, drug-target exploration, and literature interpretation across healthy and disease states. We evaluated MechAInistic on two immune-cell therapeutic hypothesis-generation tasks. For rheumatoid arthritis versus healthy naive B-cell models, it identified mitochondrial metabolic rewiring and nominated Devimistat/CPI-613 as an investigational OGDH-centered hypothesis. For multiple sclerosis CD4+ Th17 versus healthy models, it identified NADP-dependent isocitrate dehydrogenase as a candidate target and proposed ivosidenib, with vorasidenib as a mechanistically complementary alternative. Comparator analyses against general-purpose LLM systems showed that plausible biological narratives can lack auditable model grounding, whereas MechAInistic preserves the computational reasoning path from prompt to result. GRAPHICAL ABSTRACT O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=83 SRC="FIGDIR/small/723319v4_ufig1.gif" ALT="Figure 1"> View larger version (19K): org.highwire.dtl.DTLVardef@4e591eorg.highwire.dtl.DTLVardef@1bceee3org.highwire.dtl.DTLVardef@e7a0f4org.highwire.dtl.DTLVardef@f80b3a_HPS_FORMAT_FIGEXP M_FIG C_FIG
02 /Specification & Classification
Click any tag to browse matching papers- Citations
- 0
- Assay
- Research Focus
- Approach
Reproducibility ledger
Nobody has reported trying to reproduce this paper yet. Did you replicate an experiment or run the code? Your report saves the next lab a week.
Sign in to file a reproducibility report.
Related papers
- Medea: An AI agent for therapeutic reasoning across biological contexts
Pengwei Sui, Michelle M. Li, … Marinka Žitnik·bioRxiv·Jul 17, 2026
- Harness engineering enables a multi-agent LLM system to generate cross-domain hypotheses beyond single-investigator reach
Takeshi Ōmasa, Keiro Watanabe·bioRxiv·Oct 30, 2026
- Agentomics: An Agentic System that Autonomously Develops Novel State-of-the-art Solutions for Biomedical Machine Learning Tasks
Vlastimil Martinek, Andrea Gariboldi, … Panagiotis Alexiou·BioinformaticsPeer-reviewed·Jul 1, 2026
- BioScientist Agent: Designing LLM-Biomedical Agents with KG-Augmented RL Reasoning Modules for Drug Repurposing and Mechanistic of Action Elucidation
Fan Zhang, Yalong Zhao, … Lipeng Lai·bioRxiv·Aug 8, 2025
- BiomniBench: Process-level Evaluation of LLM Agents for Real-world Biomedical Research
Yuanhao Qu, Yingzhou Lu, … Kexin Huang·bioRxiv·May 18, 2026
- BioML-bench: Evaluation of AI Agents for End-to-End Biomedical ML
Henry E. Miller, Matthew Greenig, … Bo Wang·bioRxiv·Sep 1, 2025