Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question Answering

Sen Zhao; Lincheng Zhou; Yue Chen; Ding Zou

cs.AIFeb 22, 2026

Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question Answering

Authors: Sen Zhao, Lincheng Zhou, Yue Chen, Ding Zou

Organizations: Academy of Advanced Interdisciplinary Studies, Chongqing University of Posts and Telecommunications, Chongqing, China · School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China · Intelligent System Department, Zhongxing Telecom Equipment (ZTE), Changsha, Hunan, China

Abstract

Retrieval-Augmented Generation (RAG) enhances the reasoning ability of Large Language Models (LLMs) by dynamically integrating external knowledge, thereby mitigating hallucinations and strengthening contextual grounding for structured data such as graphs. Nevertheless, most existing RAG variants for textual graphs concentrate on low-dimensional structures -- treating nodes as entities (0-dimensional) and edges or paths as pairwise or sequential relations (1-dimensional), but overlook cycles, which are crucial for reasoning over relational loops. Such cycles often arise in questions requiring closed-loop inference about similar objects or relative positions. This limitation often results in incomplete contextual grounding and restricted reasoning capability. In this work, we propose Topology-enhanced Retrieval-Augmented Generation (TopoRAG), a novel framework for textual graph question answering that effectively captures higher-dimensional topological and relational dependencies. Specifically, TopoRAG first lifts textual graphs into cellular complexes to model multi-dimensional topological structures. Leveraging these lifted representations, a topology-aware subcomplex retrieval mechanism is proposed to extract cellular complexes relevant to the input query, providing compact and informative topological context. Finally, a multi-dimensional topological reasoning mechanism operates over these complexes to propagate relational information and guide LLMs in performing structured, logic-aware inference. Empirical evaluations demonstrate that our method consistently surpasses existing baselines across diverse textual graph tasks.

Figures & tables

Figure 1: Illustration of question answering with varying dimensional topological characteristics.

Figure 2: The overview of Topology-enhanced Retrieval-Augmented Framework.

Setting	Method	ExplaGraphs	SceneGraphs	WebQSP
Inference-only	Zero-shot	0.5650	0.3974	41.06
	Zero-CoT	0.5704	0.5260	51.30
	CoT-BAG	0.5794	0.5680	39.60
	KAPING	0.6227	0.4375	52.64
Frozen LLM w/ PT	Prompt tuning	0.5763	0.6341	48.34
	GraphToken	0.8508	0.4903	57.05

Table 1: Performance comparison across ExplaGraphs , SceneGraphs , and WebQSP datasets under different configurations. The bold numbers indicate that the improvement of our model over the baselines is statistically significant with (p-value

<0.01

), and the best baseline results are underlined

Method	ExplaGraphs (Accuracy)	WebQSP (Hit)
w/o CRL	0.8576	84.96
w/o TSR	0.8524	84.23
w/o MTR	0.8611	85.46
TopoRAG	0.9151	90.66

Table 2: Ablation Study on ExplaGraphs and WebQSP Datasets.

Figure 3: (a) Effect of layers

L\in\{2,3,4,5\}

on TopoRAG performance: WebQSP (Hit) and ExplaGraphs (Accuracy). (b) Effect of top-

k

k\in\{0,1,2,3\}

on TopoRAG performance: WebQSP (Hit) and SceneGraphs (Accuracy).

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Notation	Definition
$\mathcal{G}$	The input textual graph, defined as $\mathcal{G}=(V,E,\{t_{n}\}_{n\in V},\{t_{e}\}_{e\in E})$ .
$V$ , $E$	The sets of vertices (nodes) and edges in the graph $\mathcal{G}$ .
$t_{n}$ , $t_{e}$	The text attributes associated with node $n\in V$ and edge $e\in E$ .
$X$	The regular cell complex constructed from the graph $\mathcal{G}$ .
$X^{(d)}$	$d$ -skeleton.
$x^{k}$	A $k$ -dimensional cell in the complex (e.g., $x^{0}$ : a 0-cell, $x^{1}$ : a 1-cell).

Appendix

Table 3: Notation and definitions used in the TopoRAG framework.

Dataset	ExplaGraphs	SceneGraphs	WebQSP
Number of Graphs	2,766	100,000	4,737
Average Nodes	5.17	19.13	1,370.89
Average Edges	4.25	68.44	4,252.37
Node Features	Commonsense concepts	Object properties ( e.g., color, shape)	Freebase entities
Edge Features	Commonsense relations	Object interactions and spatial relations	Freebase relations
Task Type	Commonsense reasoning	Scene graph QA	Knowledge graph QA

Appendix

Table 4: Overview of datasets used in the GraphQA benchmark.

Method	ExplaGraphs (Accuracy)	SceneGraphs (Accuracy)	WebQSP (Hit)
DFS	0.9151	0.8768	90.66
BFS	0.9025	0.8725	90.18
Random	0.9187	0.8698	90.03

Appendix

Table 5: Performance comparison of different spanning tree algorithms

Dataset	$k$	Number of Cells per Dimension
Dataset	$k$	0-cells	1-cells	2-cells
WebQSP	1	15	17	2
WebQSP	2	16	18	3
	3	17	20	4
SceneGraphs	1	9	12	4
SceneGraphs	2	9	13	5

Appendix

Table 6: Impact of Top-

K

Selection on Subcomplex Retrieval.

Setting	Method	ExplaGraphs		SceneGraphs
Setting	Method	Hit	Time	Accuracy	Time
Frozen LLM w/ PT	G-Retriever	0.8516	2.6 min/epoch	0.8131	267 min/epoch
Frozen LLM w/ PT	TopoRAG	0.8899	3.0 min/epoch	0.8362	300 min/epoch
Tuned LLM	G-Retriever w/ LoRA	0.8705	3.0 min/epoch	0.8683	285 min/epoch
Tuned LLM	TopoRAG w/ LoRA	0.9151	3.3 min/epoch	0.8768	310 min/epoch

Appendix

Table 7: Performance and Efficiency Comparison of TopoRAG and G-Retriever on ExplaGraphs and SceneGraphs Datasets.

Graph Retrieval-Augmented Generation

Graph Retrieval-Augmented Generation connects language models to knowledge graphs to retrieve relational evidence for grounded, multi-hop answers.

See all 232 papers

Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG
May 7, 2026Jiarui Zhong, Hong Cai ChenRetrieval-Augmented Generation Graph Retrieval-Augmented Generation
School of Automation, Southeast University, Nanjing 210096, China
Mixture of Demonstrations for Textual Graph Understanding and Question Answering
Mar 23, 2026Yukun Wu, Lihui LiuGraph Retrieval-Augmented Generation Retrieval-Augmented Generation
Wayne State University
Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs
Jun 29, 2026Gianluca Bonifazi, Christopher Buratti, Michele Marchetti +5Multi-Hop QA Graph Retrieval-Augmented Generation
aUniversità Politecnica delle Marche, Ancona, Italy · bUniversità di Modena e Reggio Emilia, Modena, Italy

May 7, 2026J/K move · Enter open · S save

Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG

Jiarui Zhong, Hong Cai Chen

School of Automation, Southeast University, Nanjing 210096, China

Retrieval-Augmented Generation Graph Retrieval-Augmented Generation Graph-Based Retrieval Multi-Hop Reasoning

Open paper AskPDF arXiv

Retrieval-Augmented Generation (RAG) has become a core paradigm for enhancing factual grounding and multi-hop reasoning in Large Language Models (LLMs). Traditional text-based RAG often retrieves logically irrelevant pseudo-evidence, while graph-based RAG is frequently hindered by search-time pruning, which may discard potentially valid reasoning paths. Existing hybrid approaches primarily adopt simple evidence concatenation or unidirectional enhancement, which fails to address the fundamental "Information Island" problem caused by asymmetric reasoning flows between unstructured text and structured graphs. We propose TGS-RAG, a unified framework for Text-Graph Synergistic enhancement. TGS-RAG introduces a bidirectional mechanism: (i) a Graph-to-Text channel that employs a Global Voting strategy from visited graph nodes to re-rank and refine textual evidence, filtering out semantic noise; and (ii) a Text-to-Graph channel that utilizes the Memory-based Orphan Entity Bridging algorithm. This algorithm utilizes textual cues to proactively resurrect valid but previously pruned reasoning paths from the search history without additional database overhead. Experimental results on multiple multi-hop reasoning benchmarks demonstrate that TGS-RAG significantly outperforms state-of-the-art baselines, achieving a superior balance between retrieval precision and computational efficiency.

Abstract

Graph Retrieval-Augmented Generation

Explore similar work

Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG

Mixture of Demonstrations for Textual Graph Understanding and Question Answering

Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs