A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

• URL: http://arxiv.org/abs/2508.21148v2
• Date: Sat, 18 Oct 2025 04:52:16 GMT
• Title: A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
• Abstract summary: Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research.<n>This survey reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate.<n>We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge.
• Score: 251.23085679210206
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the complex nature of scientific data. This survey presents a comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate. We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge, emphasizing the multimodal, cross-scale, and domain-specific challenges that differentiate scientific corpora from general natural language processing datasets. We systematically review recent Sci-LLMs, from general-purpose foundations to specialized models across diverse scientific disciplines, alongside an extensive analysis of over 270 pre-/post-training datasets, showing why Sci-LLMs pose distinct demands -- heterogeneous, multi-scale, uncertainty-laden corpora that require representations preserving domain invariance and enabling cross-modal reasoning. On evaluation, we examine over 190 benchmark datasets and trace a shift from static exams toward process- and discovery-oriented assessments with advanced evaluation protocols. These data-centric analyses highlight persistent issues in scientific data development and discuss emerging solutions involving semi-automated annotation pipelines and expert validation. Finally, we outline a paradigm shift toward closed-loop systems where autonomous agents based on Sci-LLMs actively experiment, validate, and contribute to a living, evolving knowledge base. Collectively, this work provides a roadmap for building trustworthy, continually evolving artificial intelligence (AI) systems that function as a true partner in accelerating scientific discovery.

Related papers

• SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning [54.194672921128785]
  We introduce SciResearcher, a fully automated agentic framework for frontier-science data construction.<n>SciResearcher synthesizes diverse conceptual and computational tasks grounded in academic evidence.<n>We develop SciResearcher-8B, an agent foundation model that achieves 19.46% on the HLE-Bio/Chem-Gold benchmark.
  arXiv  Detail & Related papers  (2026-05-02T15:26:45Z)
• SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scientific Data [31.749503531377812]
  We propose SciHorizon-DataEVA, a novel agentic system to scalable AI-readiness evaluation of scientific data.<n>At the evaluation-criteria level, we introduce the Sci-TQA2 principles, which organize AI-readiness into four complementary dimensions: Governance Trustworthiness, Data Quality, AI Compatibility, and Scientific Adaptability.<n>Our Sci-TQA2-Eval dynamically constructs dataset-aware evaluation specifications by combining lightweight dataset profiling, applicability-aware metric activation, and knowledge-augmented planning.
  arXiv  Detail & Related papers  (2026-04-29T13:11:53Z)
• Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration [63.61423859450929]
  This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses.<n>We identify key methodological research priorities, including Bayesian inference at scale, physics-informed methods, validation frameworks, and active learning for discovery.
  arXiv  Detail & Related papers  (2026-01-20T18:46:42Z)
• WildSci: Advancing Scientific Reasoning from In-the-Wild Literature [50.16160754134139]
  We introduce WildSci, a new dataset of domain-specific science questions automatically synthesized from peer-reviewed literature.<n>By framing complex scientific reasoning tasks in a multiple-choice format, we enable scalable training with well-defined reward signals.<n>Experiments on a suite of scientific benchmarks demonstrate the effectiveness of our dataset and approach.
  arXiv  Detail & Related papers  (2026-01-09T06:35:23Z)
• Dynamic Knowledge Exchange and Dual-diversity Review: Concisely Unleashing the Potential of a Multi-Agent Research Team [53.38438460574943]
  IDVSCI is a multi-agent framework built on large language models (LLMs)<n>It incorporates two key innovations: a Dynamic Knowledge Exchange mechanism and a Dual-Diversity Review paradigm.<n>Results show that IDVSCI consistently achieves the best performance across two datasets.
  arXiv  Detail & Related papers  (2025-06-23T07:12:08Z)
• SciCUEval: A Comprehensive Dataset for Evaluating Scientific Context Understanding in Large Language Models [35.839640555805374]
  SciCUEval is a benchmark dataset tailored to assess the scientific context understanding capability of Large Language Models (LLMs)<n>It comprises ten domain-specific sub-datasets spanning biology, chemistry, physics, biomedicine, and materials science, integrating diverse data modalities including structured tables, knowledge graphs, and unstructured texts.<n>It systematically evaluates four core competencies: Relevant information identification, Information-absence detection, Multi-source information integration, and Context-aware inference, through a variety of question formats.
  arXiv  Detail & Related papers  (2025-05-21T04:33:26Z)
• From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery [67.07598263346591]
  Large Language Models (LLMs) are catalyzing a paradigm shift in scientific discovery.<n>This survey systematically charts this burgeoning field, placing a central focus on the changing roles and escalating capabilities of LLMs in science.
  arXiv  Detail & Related papers  (2025-05-19T15:41:32Z)
• Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents [11.74019905854637]
  Large language models (LLMs) are evolving into scientific agents that automate critical tasks.<n>Unlike general-purpose LLMs, specialized agents integrate domain-specific knowledge, advanced tool sets, and robust validation mechanisms.<n>We highlight why they differ from general agents and the ways in which they advance research across various scientific fields.
  arXiv  Detail & Related papers  (2025-03-31T13:11:28Z)
• BLADE: Benchmarking Language Model Agents for Data-Driven Science [18.577658530714505]
  LM-based agents equipped with planning, memory, and code execution capabilities have the potential to support data-driven science. We present BLADE, a benchmark to automatically evaluate agents' multifaceted approaches to open-ended research questions.
  arXiv  Detail & Related papers  (2024-08-19T02:59:35Z)
• A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery [68.48094108571432]
  Large language models (LLMs) have revolutionized the way text and other modalities of data are handled. We aim to provide a more holistic view of the research landscape by unveiling cross-field and cross-modal connections between scientific LLMs.
  arXiv  Detail & Related papers  (2024-06-16T08:03:24Z)
• End-to-end Phase Field Model Discovery Combining Experimentation, Crowdsourcing, Simulation and Learning [9.763339269757227]
  We present Phase-Field-Lab platform for end-to-end phase field model discovery. Phase-Field-Lab combines (i) a streamlined annotation tool which reduces the annotation time; (ii) an end-to-end neural model which automatically learns phase field models from data; and (iii) novel interfaces and visualizations. Our platform is deployed in the analysis of nano-structure evolution in materials under extreme conditions.
  arXiv  Detail & Related papers  (2023-09-13T22:44:04Z)
• When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System [6.445323648941926]
  Geoscience foundation models (GFMs) are a paradigm-shifting solution, integrating extensive cross-disciplinary data to enhance the simulation and understanding of Earth system dynamics. The unique strengths of GFMs include flexible task specification, diverse input-output capabilities, and multi-modal knowledge representation. This review offers a comprehensive overview of emerging geoscientific research paradigms, emphasizing the untapped opportunities at the intersection of advanced AI techniques and geoscience.
  arXiv  Detail & Related papers  (2023-09-13T08:44:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.