Jul 2026· Journal of the Royal Society Interface· Vol 23 240· 2 citations· 67 references
Medicine
Abstract
Automation is transforming scientific discovery by enabling systematic exploration of complex hypotheses. Large language models (LLMs) perform well across diverse tasks and promise to accelerate research, but often struggle with logical structures. Here, we present a framework for biological discovery integrating LLM-based agents with laboratory automation, guided by logical scaffolds incorporating symbolic relational learning, structured vocabularies and experimental constraints. This integration improves coherence and reliability in automated workflows. We couple this AI-driven approach to automated cell-culture and metabolomics platforms, enabling integrated hypothesis validation and refinement, yielding a flexible discovery system. The system identified novel interactions in Saccharomyces cerevisiae, including glutamate-induced growth inhibition in spermine-treated cells and aminoadipate's partial rescue of formic-acid stress. All hypotheses, experiments and data are captured in a graph database employing controlled vocabularies. Existing ontologies are extended, and a novel representation of scientific hypotheses is presented using description logics. This work demonstrates the potential for a reliable machine-driven discovery process in systems biology.
This article examines the emerging paradigm of agentic AI for scientific discovery, traces the conceptual shift from tools to agents, lays out a six-stage workflow spanning literature synthesis to manuscript generation, and reviews practical systems in chemistry, equation discovery, materials science, and general machine learning research.
Alexander Taktakidze· Longevity Horizon· 0 citations
Automatic scientific discovery has long been a goal of computational scholars - a machine that can discover nature's secrets on its own, moving computational systems beyond data-fitting tools toward the generation and refinement of mechanistic models of the universe. Recent advances in symbolic regression (SR) and large-language-model (LLM)-based agents suggest that such systems can recover equations from data, incorporate domain priors, and automate parts of the research workflow. However, most existing approaches either focus on narrow equation-discovery benchmarks or broad end-to-end automation pipelines, while biological systems remain comparatively underexplored. Here, we introduce the MEDA system, an LLM- and SR-powered agentic framework for discovering ordinary-differential-equation (ODE) models of biological and biologically inspired dynamical systems. MEDA retrieves background knowledge, defines admissible variables, generates mechanistic constraints, proposes candidate ODEs, and fits and evaluates them. We evaluate it across canonical model retrieval, reasoning-based extrapolation to unseen variants, and open-ended discovery, with and without experimental data. Across these settings, MEDA recovered the correct state variables, achieved strong structural recovery in retrieval and extrapolation tasks, and produced biologically plausible discovery-oriented models. Ablation and robustness analyses show that knowledge-guided formalization and mechanistic constraints are load-bearing components, whereas numerical fitting alone can preserve trajectory-compatible but biologically incorrect equations.
D. Krongauz, A. Zulti, Eran Segal et al.· 0 citations
Summary Genomics has entered a phase in which AI agents can autonomously discover, configure, execute, and chain bioinformatics operations from natural-language instructions. We term this paradigm “agentic genomics”: the delegation of multi-step genomic analyses to autonomous software agents that select tools, manage dependencies, and adapt execution in response to intermediate results, mediated by large language models (LLMs) and constrained by domain-specific skill libraries. We argue that agentic genomics shifts the bottleneck in computational biology from pipeline construction to validation. We examine emerging systems, including CellAtria, AutoBA, Bio-Copilot, and ClawBio, and assess their divergent architectures. We propose a tiered validation framework spanning research-grade, benchmarked, and clinical-grade analyses and argue that equity-aware design must be a systems requirement rather than an optional aspiration. We identify the infrastructure needed to make agentic genomics trustworthy.
M. Corpas, H. Guio, S. Fatumo· Cell Genomics· 0 citations
Mechanist is an agentic system that uses AI as a scientific instrument for the autonomous discovery of mechanisms underlying AI intelligence, and develops a mechanism theory of belief, revealing how models represent world knowledge, form beliefs, infer the beliefs of others, and how these mechanisms emerge during pretraining.
Mengru Wang, Junfeng Fang, Shuofei Qiao et al.· 0 citations
ReasFlow is introduced, an end-to-end autonomous agent system for reasoning-centric scientific discovery that operationalizes a collaborative paradigm where the human expert acts as Principal Investigator while the agent executes rigorous derivations as a capable graduate student.
Yutong He, Daibo Li, Guohong Li et al.· 1 citation
A task-adaptive large reasoning model that integrates chemical knowledge through a synergistic multispecialist architecture, chain-of-thought supervision, and molecule-informed reinforcement learning is presented, demonstrating a versatile multitask framework for knowledge-guided molecular reasoning and design.
Pengfei Liu, Shuang Ge, Xiaobo Wang et al.· Journal of Physical Chemistr...· 0 citations