English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers (arXiv 2508.21148)

Forum topic · 小凯 · 2026-07-05

Summary

This forum post introduces a large-scale survey titled "A Survey of Scientific LLMs: From Data Foundations to Agent Frontiers," available on arXiv (2508.21148), authored by Ming Hu, Chenglong Ma, Wei Li, Wanghan Xu, Jiamin Wu, Jucheng Hu and roughly 120 contributors in total. The survey maps the rapidly evolving field of scientific large language models, covering data foundations (corpora, benchmarks, data quality) through to agentic frontiers such as tool use, multi-agent collaboration, and deep research systems. The forum discussion situates the paper within the broader landscape of neural information retrieval and LLM-based systems: dense retrieval, late interaction (e.g., ColBERT), generative IR, RAG, and agentic search as sequential decision-making. It outlines a taxonomy spanning modeling paradigms, LLM integration patterns, optimization objectives, and evaluation protocols (offline metrics like nDCG/MRR, LLM-as-judge, human evaluation), and traces the timeline from BERT/DPR-era neural retrieval to 2025 trends in RL-trained search agents, Deep Research, and GraphRAG. Open problems highlighted include evaluation reliability, latency and cost, hallucination and safety, cross-lingual and multimodal generalization, and the gap between paper-reported metrics and production constraints.

A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers (Oct 2025, arXiv)

Meta Information

| Field | Content | |-------|---------| | Title | A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers | | Authors / Affiliations | Ming Hu, Chenglong Ma, Wei Li, Wanghan Xu, Jiamin Wu, Jucheng Hu, et al. (120 authors in total) | | Published | October 2025 (arXiv) | | Link | https://arxiv.org/abs/2508.21148 | | Type | Survey | | Section | Deep Research |

One-line Summary

A comprehensive survey of scientific large language models (Sci-LLMs), tracing the field from data foundations to agentic frontiers such as tool use and autonomous research agents.

Background and Motivation

The survey addresses the rapidly growing intersection of LLMs and scientific research. As LLMs move from general-purpose chat systems toward domain-specific applications in science, questions around training data quality, domain adaptation, evaluation, and agentic capabilities (tool calling, multi-step reasoning, autonomous experimentation) become central. This work aims to systematically organize the theory and practice of this cross-disciplinary field.

Key Contributions

  • Provides a unified taxonomy that brings scattered work on scientific LLMs into a comparable framework.
  • Decomposes method components (data curation, representation learning, retrievers, planners, generators, feedback mechanisms) for easier engineering adoption.
  • Offers reproducible benchmarks, datasets, and classification tables, lowering the entry barrier for new researchers.
  • Discusses interfaces with emerging paradigms: LLM tool use, reinforcement learning, multi-agent collaboration, and paths from research prototypes to production systems.
  • Lists open problems: evaluation trustworthiness, latency and cost, hallucination and safety, cross-lingual and multimodal scaling.
  • Taxonomy

    | Dimension | Subclasses | Representative Approaches | Strengths | Limitations | |-----------|-----------|---------------------------|-----------|-------------| | Modeling paradigm | Discriminative retrieval / Generative retrieval | Bi-encoders, cross-encoders, DSI, GPT indexing | Mature, scalable | Semantic drift, update cost | | LLM integration | RAG / Agent / Tool-use | Retrieval augmentation, search agents, API calling | Flexible, interpretable | Latency, error propagation | | Optimization objectives | Relevance / Diversity / Freshness | Multi-objective LTR, RLHF, online learning | Business-aligned | Scarce annotations | | Evaluation | Offline / Online / Human | nDCG, MRR, LLM-as-judge, A/B testing | Comparable | Diverges from real satisfaction |

    Research Timeline and Evolution

  • 2019–2021: BERT re-ranking and DPR lay the foundation for neural retrieval.
  • 2022–2023: RAG and FreshLLMs drive retrieval-generation fusion.
  • 2024 onward: Conversational/agentic search and generative recommender systems (Gen-RecSys) explode.
  • 2025–2026: RL-trained search agents, Deep Research systems, and GraphRAG become new growth frontiers.
  • Evaluation Paradigms

    Typical benchmarks and trends covered:

  • Datasets: MS MARCO, BEIR, Natural Questions, domain-specific corpora.
  • Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency, token cost.
  • Baselines: BM25, dense retrieval, cross-encoder re-ranking, retrieval-free LLMs, commercial search APIs.
  • Ablations: contribution of retrieval steps, re-ranking depth, and training data scale.
  • For exact quantitative results, refer to the tables in the original PDF.

    Key Takeaways

    1. Architecture: Cascaded retrieval + re-ranking + generation remains mainstream, but the agentic paradigm makes "when and how often to retrieve" a learnable decision. 2. Data: High-quality instruction data and click/session logs are equally critical; synthetic data must guard against leakage and distribution shift. 3. Evaluation: The gap between offline metrics and online satisfaction is widening; LLM-as-judge needs cross-validation with human evaluation. 4. Productization: Latency, cost, interpretability, and safety are hard constraints for industrial deployment—not just academic benchmarks.

    Open Problems and Future Directions

    The authors highlight: insufficient unified benchmarks, non-reproducible private data, LLM evaluation bias, and safety/cost constraints for agentic systems. Future directions include finer-grained process supervision, joint retrieval-reasoning training, enterprise metadata governance, and multimodal/cross-lingual consistency.

    Limitations

    Possible limitations include experiment scale constrained by GPU budgets, mismatch between benchmarks and real user distributions, English-centric data limiting cross-lingual generalization, and safety risks of open-web agent systems.

    Related Entries

  • A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications
  • A Survey of LLM-based Deep Search Agents
  • Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
  • Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning
  • References

  • Original paper: A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers, arXiv 2508.21148.

Tags

#scientific-llms#survey#deep-research#rag#agentic-search#information-retrieval#llm-agents#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208598