# MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic Models

arXiv: https://arxiv.org/abs/2607.18249 · HTML: https://mlsanity.com/paper/2607.18249/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 10 of its 74 references that are in the map.
- First posted on arXiv 8 May 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 10 of 10)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [Parallelizing the dual revised simplex method](https://mlsanity.com/paper/1503.01889/) (2015)
- [An Agentic System for Rare Disease Diagnosis with Traceable Reasoning](https://mlsanity.com/paper/2506.20430/) (2025)
- [SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration](https://mlsanity.com/paper/2507.20280/) (2025)
- [The National Research Platform: Stretched, Multi-Tenant, Scientific Kubernetes Cluster](https://mlsanity.com/paper/2505.22864/) (2025)
- [Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing](https://mlsanity.com/paper/2406.06723/) (2024)
- [From Knowledge Generation to Knowledge Verification: Examining the BioMedical Generative Capabilities of ChatGPT](https://mlsanity.com/paper/2502.14714/) (2025)
- [From Prompt to Pipeline: Large Language Models for Scientific Workflow Development in Bioinformatics](https://mlsanity.com/paper/2507.20122/) (2025)

## Abstract (arXiv)

Constraint-based metabolic modeling is a powerful way to study the mechanistic basis of cellular states and disease, but its effective use demands substantial computational expertise and careful coordination of multi-step analyses. We developed MechAInistic to lower this barrier and enable researchers to ask complex biological questions in natural language. Harnessing large language models, MechAInistic is a multi-agent system organized around an Architect-Reviewer pattern that transforms a natural-language question into an executable, model-grounded workflow and generates a structured report. The system supports a variety of tasks, including pathway comparison, perturbation analysis, drug-target exploration, and literature-grounded interpretation across paired metabolic model states. We developed and evaluated MechAInistic using two paired immune-cell metabolic-model use cases for therapeutic hypothesis generation. For Naive B cells from rheumatoid arthritis (RA) paired with healthy controls, MechAInistic identified mitochondrial metabolic rewiring and nominated Devimistat/CPI-613 as an investigational OGDH-centered hypothesis. In a paired CD4+ Th17 cell study from multiple sclerosis (MS) and healthy controls, the same workflow identified NADP-dependent isocitrate dehydrogenase as the optimal single target and proposed ivosidenib as an FDA-approved repurposing candidate. Together, these results show that MechAInistic converts natural-language biological questions into executable, model-grounded workflows for traceable therapeutic hypothesis generation.