mlsanityData to 14 Oct 2026

RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval

arXiv 2506.08625 ↗First posted 10 Jun 2025cs.CLcited by 1

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Scientific reasoning requires not only long-chain reasoning processes, but also knowledge of domain-specific terminologies and adaptation to updated findings. To deal with these challenges for scientific reasoning, we introduce RAISE, a step-by-step retrieval-augmented framework which retrieves logically relevant documents from in-the-wild corpus. RAISE is divided into three steps: problem decomposition, logical query generation, and logical retrieval. We observe that RAISE consistently outperforms other baselines on scientific reasoning benchmarks. We analyze that unlike other baselines, RAISE retrieves documents that are not only similar in terms of the domain knowledge, but also documents logically more relevant.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 42 of its 47 references that are in the map. First posted on arXiv 10 Jun 2025.

Builds on

42 of 47 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery22 Mar
  2. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  3. 2025HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation18 Feb
  4. 2025Chain-of-Retrieval Augmented Generation24 Jan
  5. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  6. 2024SciAgent: Tool-augmented Language Models for Scientific Reasoning18 Feb

Other references · 36

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  8. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  9. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  10. 2017Billion-scale similarity search with GPUscited by 2,497
  11. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  12. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
24 more
  1. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  2. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  3. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  4. 2022Galactica: A Large Language Model for Sciencecited by 744
  5. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  6. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  7. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  8. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 331
  9. 2024Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMscited by 273
  10. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 159
  11. 2024The Impact of Reasoning Step Length on Large Language Modelscited by 153
  12. 2024ChemLLM: A Chemical Large Language Modelcited by 106
  13. 2025HalluLens: LLM Hallucination Benchmarkcited by 92
  14. 2025PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoningcited by 59
  15. 2025Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Mathcited by 44
  16. 2024Not All LLM Reasoners Are Created Equalcited by 30
  17. 2025Benchmarking Retrieval-Augmented Generation for Chemistrycited by 20
  18. 2024Corpus-Steered Query Expansion with Large Language Modelscited by 17
  19. 2024VisScience: An Extensive Benchmark for Evaluating K12 Educational Multi-modal Scientific Reasoningcited by 13
  20. 2025Credible Plan-Driven RAG Method for Multi-Hop Question Answeringcited by 12
  21. 2023Predictive Chemistry Augmented with Text Retrievalcited by 10
  22. 2025Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answerscited by 10
  23. 2024Stepwise Self-Consistent Mathematical Reasoning with Large Language Modelscited by 8
  24. 2024A Statistical Framework for Data-dependent Retrieval-Augmented Modelscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertaintycited by 9

Similar, not cited

Close in wording, no citation either way

  1. 2023Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning
  2. 2026IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs
  3. 2025Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim rightarrow Evidence Reasoning
  4. 2026Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning Capabilities
  5. 2025Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning
  6. 2026SPARK: Skeleton-Guided Reasoning Synthesis from Large-Scale Scientific Literature
  7. 2025HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance
  8. 2026Large Knowledge Model: From Papers to a Scientific Reasoning Landscape