Large language model agents for biological intelligence across genomics, proteomics, spatial biology, and biomedicine
Агенты на основе больших языковых моделей для биологического интеллекта в геномике, протеомике, пространственной биологии и биомедицине
2026-03-01
SCID: 54.1/egbe6xaq
Discuss with AI
automated bioinformatics workflowsbiological intelligenceclosed-loop experimental designlarge language model agentsmultimodal reasoning
Figures from the paper
Abstract (AI)
Large language models (LLMs) are evolving from passive predictors into agentic systems capable of planning, tool-use, and multimodal reasoning. This shift is especially consequential for biology, where complex, noisy, and multi-scale data require adaptive and integrative computational strategies. In this review, we provide the first systematic synthesis of LLM-based agents across genomics, molecular biology, imaging, biomedical analysis, and automated bioinformatics workflows. We analyze >60 emerging systems and organize them within a unifying framework that characterizes agentic traits, such as autonomous decision-making, external tool invocation, memory, and self-correction. Across domains, agentic LLMs show early promise in enabling multi-step analysis, linking heterogeneous evidence, and supporting exploratory scientific tasks. At the same time, our comparative assessment highlights consistent challenges, including unstable reasoning, limited biological grounding, retrieval misalignment, and barriers to reproducibility and biosafety. We conclude by outlining opportunities for trustworthy and collaborative biological agents, including multimodal integration, closed-loop experimental design, and robust evaluation practices. This survey aims to clarify the emerging landscape and chart a path toward reliable agentic systems for biological discovery.
Key Findings
1
Across biological domains, agentic LLMs show early promise for multi-step analysis, heterogeneous evidence integration, and exploratory scientific tasks.
2
Comparative assessment identifies recurring limitations: unstable reasoning, weak biological grounding, retrieval misalignment, and obstacles to reproducibility and biosafety.
3
It introduces a unifying framework organized around agentic capabilities including autonomous decision-making, external tool use, memory, and self-correction.
4
The review highlights multimodal integration, closed-loop experimental design, and robust evaluation as priorities for trustworthy biological agents.
5
The review systematically synthesizes more than 60 LLM-based agent systems spanning genomics, molecular biology, imaging, biomedical analysis, and bioinformatics workflows.
Research Object
LLM-based agents applied to biological research across genomics, proteomics, spatial biology, imaging, molecular biology, biomedicine, and bioinformatics workflows
Research Subject
Their agentic capabilities, applications, comparative performance, and challenges in autonomous multi-step biological analysis and discovery
Publication Details
Publication Date
2026-03-01
Journal
Publisher
ISSN
Cited by
13
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest