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 (Oct 2025, arXiv)

Forum topic · 小凯 · 2026-07-05

Summary

This forum post on zhichai.net discusses a large-scale survey paper, 'A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers' (arXiv:2508.21148, October 2025), authored by Ming Hu, Chenglong Ma, Wei Li, Wanghan Xu, Jiamin Wu, Jucheng Hu and roughly 120 collaborators. The post positions the survey at the intersection of agentic search and large-scale search, recommendation, and personalization systems, arguing that traditional pipelines that separate retrieval, ranking, and generation struggle to meet LLM-era demands for natural-language interaction, multi-hop reasoning, and up-to-date knowledge. It organizes the field along a taxonomy covering modeling paradigms (discriminative vs. generative retrieval), LLM integration (RAG, agents, tool use), optimization objectives, and evaluation protocols. It also outlines an evolution timeline from BERT/DPR through RAG to reinforcement-learning-trained search agents, Deep Research, and GraphRAG, and lists open problems such as benchmark reliability, latency and cost, hallucination and safety, and cross-lingual and multimodal scaling. The post includes engineering checklists, a glossary, and cross-references to related surveys on deep research and LLM-based search agents.

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

Overview

  • 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)
  • Link: https://arxiv.org/abs/2508.21148
  • Type: Survey
  • Category: Deep Research
  • Background and Motivation

    In large-scale search, recommendation, and personalization systems, agentic search has long faced challenges in efficiency, scalability, and user-intent understanding. Traditional pipeline approaches often treat retrieval, ranking, and generation as disjoint stages, making it hard to meet LLM-era demands for natural-language interaction, multi-hop reasoning, and real-time knowledge. This survey aims to systematically map the theoretical and practical boundaries of this intersection, covering open-domain information access, enterprise knowledge retrieval, conversational search, semantic understanding in recommender systems, and end-to-end architectures that coordinate external knowledge sources with generative models.

    Key Contributions

  • A unified perspective that brings scattered related work into a comparable framework.
  • A clear decomposition of method components: representation learning, retrievers, rerankers, planners, generators, and feedback mechanisms.
  • Reproducible benchmarks, datasets, and taxonomy tables that lower the entry barrier for follow-up research.
  • Discussion of interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration, including migration paths from research prototypes to industrial systems.
  • Explicit open problems: evaluation trustworthiness, latency and cost, hallucination and safety, and cross-lingual / multimodal scaling.
  • Taxonomy

    | Dimension | Subclasses | Representative Ideas | Strengths | Limitations | |---|---|---|---|---| | Modeling paradigm | Discriminative / generative retrieval | Bi-encoders, cross-encoders, DSI, GPT-indexed corpora | Mature, scalable | Semantic drift, update cost | | LLM integration | RAG / Agent / Tool-use | Retrieval augmentation, search agents, API calls | Flexible, interpretable | Latency, error propagation | | Optimization objective | Relevance / diversity / freshness | Multi-objective LTR, RLHF, online learning | Business-aligned | Scarce labels | | Evaluation | Offline / Online / Human | nDCG, MRR, LLM-as-judge, A/B tests | Comparable | Divergence from real satisfaction |

    Main Research Lines

    The field is typically organized into four threads:

  • Dense retrieval: high recall and low latency, suited to first-stage retrieval.
  • Late interaction (e.g., ColBERT): higher precision but larger indexes.
  • Generative IR: directly "generating" documents via tokens or docids, simplifying cascades.
  • Agentic search: modeling search as sequential decision-making, supporting multi-hop reasoning and self-reflection.
  • Timeline of Evolution

  • 2019–2021: BERT reranking and DPR establish neural retrieval foundations.
  • 2022–2023: RAG and FreshLLMs drive retrieval–generation fusion.
  • 2024 onward: conversational/agentic search and Gen-RecSys proliferate.
  • 2025–2026: RL-trained search agents, Deep Research, and GraphRAG become new growth frontiers.
  • Evaluation Paradigms

    Typical setups covered by the survey include:

  • Datasets: MS MARCO, BEIR, Natural Questions, domain-specific corpora, public recommendation sets.
  • Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency and token cost.
  • Baselines: BM25, dense retrieval, cross-encoder reranking, retrieval-free LLMs, commercial search APIs.
  • Ablations: contribution of retrieval steps, reranking depth, and training-data scale.
  • Quantitative results should be verified against the original PDF tables.

    Key Takeaways for Search / Rec / Personalization

    1. Architecture: cascade retrieval + rerank + generation remains mainstream, but agentic paradigms make "how many retrievals and what policy" itself learnable. 2. Data: high-quality instruction data and click/session logs are both critical; synthetic data must guard against knowledge leakage and distribution shift. 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge needs cross-validation against human evaluation. 4. Productization: latency, cost, explainability, and safety policies are hard constraints in industry—not just academic benchmark scores.

    Open Problems and Future Directions

    Authors commonly cite: insufficient unified benchmarks, non-reproducible private data, LLM evaluation bias, and safety/cost constraints on agentic systems. Future work includes 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 leaving cross-lingual generalization unknown, and safety risks of agentic systems on the open web. Future directions include more efficient test-time compute allocation, deeper integration with knowledge graphs / structured databases, and causal and fairness constraints for recommender systems.

    Engineering Checklist

    | Item | Question | Suggestion | |---|---|---| | Data | PII in training/index? Version management? | Partitioned indexes, anonymization, rollback-able embedding versions | | Latency | p99 budget? Retrieval steps? | Cascade + early stopping, hot-query caching, async reranking | | Quality | Do offline gains translate to online CTR/satisfaction? | Interleaving experiments, human audits, citation checks | | Safety | Does open retrieval introduce poisoning/bias? | Source whitelisting, adversarial detection, output filtering | | Cost | Per-query tokens and GPU usage? | Route to smaller models, distillation, hybrid sparse+dense |

    Glossary

  • IR: Information Retrieval
  • RAG: Retrieval-Augmented Generation
  • LTR: Learning to Rank
  • nDCG: Normalized Discounted Cumulative Gain
  • Agentic Search: framing search as sequential decision-making and tool invocation
  • Gen-IR: Generative Information Retrieval
  • 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
  • AgentIR: Reasoning-Aware Retrieval for Deep Research Agents
  • Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning
  • BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical AI
  • References

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

Tags

#large-language-models#scientific-ai#survey#retrieval-augmented-generation#agentic-search#deep-research#information-retrieval#reinforcement-learning

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/178208568