Aug 2026· Longevity Horizon· 0 citations· 236 references
TL;DR
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.
Abstract
Artificial intelligence in science is undergoing a foundational change. Rather than serving as a passive analytical instrument — classifying images, predicting structures, spotting patterns — AI systems are beginning to act as autonomous research collaborators. These systems, built on large language models and tool-integrated architectures, can reason about experimental design, formulate strategies, execute multi-step workflows, and refine their approaches from empirical feedback. Often called “AI Scientists,” they participate across the full research lifecycle, from the seed of a hypothesis through to a draft manuscript. This article examines the emerging paradigm of agentic AI for scientific discovery. It 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. A central concern of the analysis is the verification crisis — the growing gap between what these systems can produce and what they can prove. We compile quantitative evidence on failure rates, analyse competing frameworks for trustworthy agentic science (Chain-of-Evidence, Audit-Closed protocols, FEV, and structural FDR enforcement), and propose actionable standards for rigorous validation. The article closes with an assessment of the field’s limitations and a set of priority directions for making agentic science trustworthy at scale.
Scientific discovery has advanced through successive transformations in the organization of knowledge. Observation and experimentation established the empirical foundations of science. Theory made it possible to derive general principles from particular phenomena. Computation extended inquiry into systems beyond direct observation, while data-intensive methods opened new spaces of pattern and prediction. Science now confronts a different frontier. The central challenge is no longer simply to produce more information, but to organize expanding knowledge, reasoning, and evidence into a coherent process of discovery. Here, we introduce Bridging Literature, Agents, and Zero-gap Experimentation (BLAZE), a paradigm of socialized scientific intelligence. BLAZE conceives AI not as an assistant for isolated research tasks, but as an organizational infrastructure for scientific discovery. It connects persistent knowledge, collective reasoning, empirical validation, and human judgment within a continuous research lifecycle, transforming fragmented activities into a cumulative process of inquiry, criticism, and revision. The central premise of BLAZE is that scientific intelligence does not arise from computation alone. It emerges from the sustained interaction among knowledge, hypotheses, experiments, and collective verification. By organizing humans and machines within a shared scientific process, BLAZE makes discovery more traceable, reproducible, and cumulative while preserving human creativity, judgment, and responsibility. Socialized scientific intelligence may provide a foundation for the next era of science. Its purpose is not to replace human discovery, but to extend the scale, depth, and continuity of collective scientific inquiry.
Xinjie Yao, Xingxin Xu, Xiyuan Gao et al.· 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
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.
Daniel Brunnsåker, Alexander H. Gower, Prajakta Naval et al.· Journal of the Royal Society...· 2 citations
A survey of the past and future of AI Scientists: machines capable of automating science, which have the potential to transform science and create a new form of science that will create a new form of science and transform the world.
The rapid evolution of large language models (LLMs) has catalyzed a shift from passive AI systems toward autonomous agentic architectures capable of reasoning, memory, tool use, and multi-agent collaboration. This bibliometric review characterizes the emerging field through 810 publications retrieved from the Web of Science Core Collection for the period 2023–2025. Annual output rose sharply over this window—from 4 publications in 2023 to 96 in 2024 and 710 in 2025—accompanied by a parallel rise in citations, indicating rapid mainstream adoption. Author-keyword analysis reveals a landscape dominated by large language models, artificial intelligence, and multi-agent systems, with agentic AI, generative AI, and retrieval-augmented generation (RAG) emerging as core themes. Research output is geographically concentrated, led by China and the United States, and is distributed across a broad range of engineering, applied-science, and domain-specific journals rather than a single specialist venue, reflecting the field's cross-disciplinary uptake. Synthesizing this corpus, we organize the technical landscape around reasoning, memory, tool integration and RAG, and multi-agent orchestration; survey application domains spanning healthcare, scientific discovery, education, and software engineering, with emerging activity in finance and law; and analyze the principal challenges—hallucination, trust and robustness, inter-agent coordination, scalability, and governance. The review provides a structured, evidence-based map of agentic AI research to orient researchers and practitioners navigating this rapidly evolving field.
Ben J. Weber, Clara M. Hofmann, Amara N. Okoye· Journal of AI Analytics and...· 0 citations
Artificial intelligence has advanced scientific discovery, but most AI4Science systems remain fragmented tools that rely on humans to coordinate problem formulation, literature grounding, model use, simulation, validation, and knowledge reuse. This paper presents \textbf{SCION (Scientific Collaborative Innovation with Agentic Organizational Nexus)}, an agentic scientific operating system that acts as an \textbf{organizational nexus}. Through a Science Agent serving as a \textbf{Meta-Harness}, SCION connects scientific tasks, tools, agents, artifacts, and memory, transforming research into an executable, auditable, and reusable operational process. At its core is the \textbf{Research Execution Plan (REP)}, which compiles high-level scientific intent into staged objectives, dependencies, verification checkpoints, tool requirements, expected artifacts, and fallback conditions. SCION further integrates hierarchical multi-agent execution, profile-driven specialization, selective context construction, governed delegation, and layered epistemic memory to support long-horizon scientific work. We formulate discovery under SCION as \textbf{Target-conditioned Inverse Search} and extend it to hidden-target settings through batch active search under finite experimental budgets. Applications in materials analysis, molecule design, and protein or antibody screening, together with experiments on scientific reading, idea generation, molecule generation, and antibody screening, show that SCION outperforms existing autonomous research-agent baselines, especially in decomposition, verification, refinement, and memory reuse. Overall, SCION shifts AI from isolated tools toward a coordinated operational layer for traceable and reusable scientific innovation.
Y. Zheng, Yuxin Wang, Jiahao Lu et al.· 0 citations