# MARBLE: Multi-Agent Reasoning for Bioinformatics Learning and Evolution

arXiv: https://arxiv.org/abs/2601.14349 · HTML: https://mlsanity.com/paper/2601.14349/

## 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 17 of its 24 references that are in the map.
- First posted on arXiv 20 Jan 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, 17 of 17)

- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [Empowering Biomedical Discovery with AI Agents](https://mlsanity.com/paper/2404.02831/) (2024)
- [AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML](https://mlsanity.com/paper/2410.02958/) (2024)
- [Tradition and Innovation in Scientists' Research Strategies](https://mlsanity.com/paper/1302.6906/) (2013)
- [BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models](https://mlsanity.com/paper/2308.16458/) (2023)
- [Human-in-the-loop or AI-in-the-loop? Automate or Collaborate?](https://mlsanity.com/paper/2412.14232/) (2024)
- [Automating the Practice of Science -- Opportunities, Challenges, and Implications](https://mlsanity.com/paper/2409.05890/) (2024)
- [NADER: Neural Architecture Design via Multi-Agent Collaboration](https://mlsanity.com/paper/2412.19206/) (2024)
- [LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World](https://mlsanity.com/paper/2506.00980/) (2025)

## Abstract (arXiv)

Motivation: Developing high-performing bioinformatics models typically requires repeated cycles of hypothesis formulation, architectural redesign, and empirical validation, making progress slow, labor-intensive, and difficult to reproduce. Although recent LLM-based assistants can automate isolated steps, they lack performance-grounded reasoning and stability-aware mechanisms required for reliable, iterative model improvement in bioinformatics workflows. Results: We introduce MARBLE, an execution-stable autonomous model refinement framework for bioinformatics models. MARBLE couples literature-aware reference selection with structured, debate-driven architectural reasoning among role-specialized agents, followed by autonomous execution, evaluation, and memory updates explicitly grounded in empirical performance. Across spatial transcriptomics domain segmentation, drug-target interaction prediction, and drug response prediction, MARBLE consistently achieves sustained performance improvements over strong baselines across multiple refinement cycles, while maintaining high execution robustness and low regression rates. Framework-level analyses demonstrate that structured debate, balanced evidence selection, and performance-grounded memory are critical for stable, repeatable model evolution, rather than single-run or brittle gains. Availability: Source code, data and Supplementary Information are available at https://github.com/PRISM-DGU/MARBLE.