Problem
Research questions and friction points this paper is trying to address.
Retrieval-Augmented Generation
Hypergraph RAG
Static Traversal
Computational Efficiency
Reasoning Depth
Asymmetric Dynamic Routing: Balancing Reasoning Depth and Computational Efficiency in Hypergraph RAG
🤖 AI Summary
This study addresses the computational redundancy and lack of complex reasoning context inherent in static retrieval for hypergraph-based Retrieval-Augmented Generation (RAG). To this end, we propose an asymmetric dynamic routing framework that introduces a novel query-intent-driven routing mechanism. Specifically, a lightweight classifier dispatches three topological traversal operators to facilitate bidirectional information flow within hierarchical knowledge graphs, effectively balancing reasoning depth with computational efficiency. Experimental results demonstrate that our approach maintains strong reasoning performance while reducing prompt token consumption by 48.7% and decreasing end-to-end latency by 45.3%.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Asymmetric Dynamic Routing
Hypergraph RAG
Hierarchical Knowledge Graphs
Intent-conditioned Retrieval
Topological Traversal Operators
🔎 Similar Papers
No similar papers found.
