Saved in:
Bibliographic Details
Main Authors: Hui, Yulong, Liu, Yihao, Lu, Yao, Zhang, Huanchen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.02603
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929742667579392
author Hui, Yulong
Liu, Yihao
Lu, Yao
Zhang, Huanchen
author_facet Hui, Yulong
Liu, Yihao
Lu, Yao
Zhang, Huanchen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_02603
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing
Hui, Yulong
Liu, Yihao
Lu, Yao
Zhang, Huanchen
Computation and Language
Information Retrieval
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.
title OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing
topic Computation and Language
Information Retrieval
url https://arxiv.org/abs/2503.02603