论文研究
arxiv.org ·
非对称动态路由：在超图 RAG 中平衡推理深度与计算效率
该论文指出基于图/超图的 RAG 系统普遍采用与查询复杂度无关的静态遍历策略，导致简单查询算力冗余、复杂推理上下文缺失，并将此称为“静态检索谬误”。作者提出 Asymmetric Dynamic Routing（ADR），一种运行在分层知识图上的意图条件化检索框架，用轻量结构化分类器将查询动态分派到三种非对称拓扑遍历算子：局部事实锚定、自底向上邻接扩散、自顶向下洞见落地，实现跨层级双向信息流。在五个领域语料上的实验显示，ADR 在保持较强推理性能的同时，prompt token 消耗最多降低 48.7%，端到端查询延迟降低 45.3%。
AI推荐理由 arXiv 预印本，摘要明确给出方法（ADR 意图条件化检索、三类非对称拓扑遍历算子）与量化结果（五个领域语料上 prompt token 消耗最多降低 48.7%、端到端查询延迟降低 45.3%），信息密度较高，属于 RAG 效率方向的可验证研究。局限在于仅为预印本、未经同行评审，且摘要未披露基线设置、数据集细节与统计显著性，效果需进一步核实。
72
正文
Computer Science > Information Retrieval
arXiv:2609.29282 (cs)
[Submitted on 24 Sep 2026]
Title:Asymmetric Dynamic Routing: Balancing Reasoning Depth and Computational Efficiency in Hypergraph RAG
Authors:Qi Sun, Yijia Zhang, Xingliang Hou, Caibo Li, Qiang Li, Yu Guo
View a PDF of the paper titled Asymmetric Dynamic Routing: Balancing Reasoning Depth and Computational Efficiency in Hypergraph RAG, by Qi Sun and 5 other authors
View PDF
HTML (experimental)
Abstract:While graph-based and hypergraph-based Retrieval-Augmented Generation (RAG) significantly mitigate hallucinations in Large Language Models (LLMs), existing structure-based RAG systems typically adopt static traversal strategies regardless of the query complexity. We identify this ``static retrieval fallacy'' as a primary source of computational redundancy for simple queries and cognitive context gaps for complex reasoning tasks. To balance reasoning quality and inference efficiency, we propose Asymmetric Dynamic Routing (ADR), an intent-conditioned retrieval framework operating over hierarchical knowledge graphs. ADR employs a lightweight structured classifier to dynamically dispatch queries among three asymmetric topological traversal operators: localized fact anchoring, bottom-up adjacency diffusion, and top-down insight grounding, which collectively enable bidirectional information flow across hierarchical knowledge layers. Extensive empirical evaluations across five domain-specific corpora demonstrate that ADR maintains strong reasoning performance while reducing prompt token consumption by up to 48.7\% and end-to-end query latency by 45.3\%, yielding a favorable quality--efficiency trade-off for query-adaptive Hypergraph RAG.
Comments:
Subjects:
Information Retrieval (cs.IR)
Cite as:
arXiv:2609.29282 [cs.IR]
(or
arXiv:2609.29282v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2609.29282
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Xingliang Hou [view email]
[v1]
Thu, 24 Sep 2026 09:17:40 UTC (163 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Asymmetric Dynamic Routing: Balancing Reasoning Depth and Computational Efficiency in Hypergraph RAG, by Qi Sun and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Additional Features
Audio Summary
Current browse context:
cs.IR
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)