mlsanityData to 14 Oct 2026

OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing

arXiv 2503.02603 ↗First posted 4 Mar 2025cs.CL cs.IRcited by 2

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Large Language Models (LLMs) encounter challenges in efficiently processing long-text queries, as seen in applications like enterprise document analysis and financial report comprehension. While conventional solutions employ long-context processing or Retrieval-Augmented Generation (RAG), they suffer from prohibitive input expenses or incomplete information. Recent advancements adopt context compression and dynamic retrieval loops, but still sacrifice critical details or incur iterative costs. To address these limitations, we propose OkraLong, a novel framework that flexibly optimizes the entire processing workflow. Unlike prior static or coarse-grained adaptive strategies, OkraLong adopts fine-grained orchestration through three synergistic components: analyzer, organizer and executor. The analyzer characterizes the task states, which guide the organizer in dynamically scheduling the workflow. The executor carries out the execution and generates the final answer. Experimental results demonstrate that OkraLong not only enhances answer accuracy but also achieves cost-effectiveness across a variety of datasets.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 31 of its 40 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

31 of 40 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024CompAct: Compressing Retrieved Documents Actively for Question Answering12 Jul
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May

Other references · 29

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  7. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  8. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  9. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  10. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  11. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  12. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 740
17 more
  1. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  2. 2021A Dataset of Information-Seeking Questions and Answers Anchored in Research Paperscited by 486
  3. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  4. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  5. 2024LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compressioncited by 348
  6. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  7. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 257
  8. 2023Focused Transformer: Contrastive Training for Context Scalingcited by 133
  9. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approachcited by 119
  10. 2022Towards Complex Document Understanding By Discrete Reasoningcited by 82
  11. 2023Extending Context Window of Large Language Models via Semantic Compressioncited by 45
  12. 2024UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysiscited by 40
  13. 2024MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexitycited by 29
  14. 2024Long Context vs. RAG for LLMs: An Evaluation and Revisitscited by 26
  15. 2024EfficientRAG: Efficient Retriever for Multi-Hop Question Answeringcited by 24
  16. 2024Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilitiescited by 16
  17. 2024Dr3: Ask Large Language Models Not to Give Off-Topic Answers in Open Domain Multi-Hop Question Answeringcited by 4

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrievalcited by 6
  2. 2025ScaleDoc: Scaling LLM-based Predicates over Large Document Collectionscited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2024MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
  2. 2024Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models
  3. 2024Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism
  4. 2024Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey
  5. 2024MemLong: Memory-Augmented Retrieval for Long Text Modeling
  6. 2025Systematic Evaluation of Optimization Techniques for Long-Context Language Models
  7. 2024A Survey of Query Optimization in Large Language Models
  8. 2025Optimizing Retrieval-Augmented Generation: Analysis of Hyperparameter Impact on Performance and Efficiency