STITCH-RAG: Spatio-Temporal Influence Tracing over Topic Hypergraphs for Multi-Hop Retrieval-Augmented Generation

Haodong Yang; Mengzhu Chen; Jia Cai

cs.IRSep 28, 2026

STITCH-RAG: Spatio-Temporal Influence Tracing over Topic Hypergraphs for Multi-Hop Retrieval-Augmented Generation

Authors: Haodong Yang, Mengzhu Chen, Jia Cai

Organizations: School of Statistics And Data Science, Guangdong University of Finance & Economics Guangzhou, China

Abstract

Multi-hop retrieval-augmented generation requires a retriever to connect evidence distributed across documents while preserving a concise, faithful generation context. Existing indexes leave two complementary gaps: chunk-based RAG can break cross-passage evidence chains, whereas an unlabeled pairwise projection without generating-topic provenance cannot jointly preserve topic-level co-participation and per-occurrence entity descriptions. We propose STITCH-RAG, a hypergraph-based framework with three coupled components. First, a semi-merged topic hypergraph encodes multi-entity co-participation as topic-summary hyperedges while retaining per-chunk entity states linked by canonical-name equivalence. Second, spatio-temporal influence bridging propagation (STIBP) combines topic-space propagation with deterministic chunk-index linkage across name-equivalent states under frequency-adaptive decay. Third, continuous STIBP scores replace binary entity-match seeds in localized Personalized PageRank (PPR). We characterize the condition under which this prior assigns more PPR mass to ground-truth evidence than a binary prior. Under the reported protocol, STITCH-RAG attains the highest reported Contain-Acc and LLM-Acc point estimates among the compared methods on HotpotQA and 2WikiMultiHopQA, and higher Recall@8 than the methods included in the standardized retrieval comparison. Results on the mixed-domain benchmark remain auxiliary preference-based evidence because only LLM-judged accuracy is available.

Figures & tables

Figure 1: Representation trade-offs for an example query about the birthplace of Film X’s director. (a) Chunk-based RAG can return locally similar but disconnected passages. (b) The illustrated unlabeled pairwise/full-merge representation retains the path through Alice Smith, but its single static entity node mixes the evidence-bearing birthplace context with unrelated contexts such as awards. The panel depicts one unlabeled full-merge representation, not all pairwise graphs. (c) STITCH-RAG preserves the two local Alice Smith states and links them by name equivalence, allowing query-conditioned propagation through topic hyperedges and across chunk-specific entity states.

Figure 2: Framework of STITCH-RAG: (1) document chunking; (2) semi-merged topic hypergraph construction, with topic-summary hyperedges and entity-description nodes linked by $\phi$ ; (3) STIBP through spatial and temporal channels; (4) influence-guided chunk scoring as a continuous PPR teleportation prior; and (5) top- $k$ chunk retrieval for answer generation.

Method	HotpotQA			2Wiki			Mix
	Contain-Acc	LLM-Acc	EM	Contain-Acc	LLM-Acc	EM	LLM-Acc
Zero-shot	0.422	0.451	0.300	0.505	0.398	0.345	0.269
Standard-RAG	0.700	0.702	0.460	0.689	0.617	0.467	0.669
HippoRAG	0.690	0.835	0.609	0.555	0.575	0.476	0.823
Cog-RAG	0.822	0.843	0.562	0.768	0.700	0.554	0.831
Hyper-RAG	0.735	0.808	0.511	0.785	0.745	0.541	0.808

Table 1: Answer accuracy on HotpotQA, 2Wiki, and Mix. Best result per column bolded. Only STITCH-RAG was repeated end to end; its entries average three runs on the same fixed question samples, with all run-level standard deviations below 0.004. Baseline run-level variances are unavailable. The table therefore ranks reported point estimates but does not establish statistical superiority.

Method	HotpotQA	2Wiki
Standard-RAG	0.612	0.587
LightRAG	0.741	0.693
LinearRAG	0.723	0.712
STITCH-RAG	0.798	0.769

Table 2: Passage-level Recall@8 on HotpotQA and 2Wiki, defined as

|G_{q}\cap R_{q}^{8}|/|G_{q}|

where

G_{q}

is the ground-truth supporting chunk set and

R_{q}^{8}

is the top-8 retrieved set. Mix is excluded because supporting-fact annotations are unavailable. Only methods with publicly available retrieval outputs under the standardized embedding protocol are included.

Variant	HotpotQA LLM-Acc	2Wiki LLM-Acc	Mix LLM-Acc
Full STITCH-RAG	0.895	0.861	0.884
w/o STIBP	0.823	0.707	0.800
w/o PPR	0.825	0.793	0.854
w/o all (dense retrieval)	0.761	0.684	0.672
w/o spatial bridging	0.838	0.742	0.814
w/o index-proximity bridging	0.840	0.748	0.815

Table 3: Ablation of STITCH-RAG (three-run LLM-Acc average). The upper block removes STIBP/PPR or uses dense retrieval; the lower block removes one STIBP channel or replaces continuous priors with binary initialization.

Method	Time (s)		Token Consumption				LLM-Acc
	Indexing	Retrieval	Idx. Prompt	Idx. Completion	Query Prompt	Query Completion
HippoRAG	1706.91	39.56	1382281	1321272	55845.91	3774.76	0.823
Cog-RAG	19109.94	126.88	3082137	7988713	36840.47	13246.30	0.831
Hyper-RAG	70414.64	52.20	4652473	7264711	18557.08	5521.35	0.808
LightRAG	89882.40	75.87	6588007	8685853	29795.00	8148.52	0.877
LinearRAG	633.37	23.00	0	0	6395.72	261.50	0.762

Table 4: Efficiency and LLM-Acc on Mix. Indexing costs are one-time; query-stage tokens include answer generation and method-specific query-time LLM calls under identical hardware and API conditions.

$\delta$	Mix
0.3	0.861
0.4	0.815
0.5	0.884
0.6	0.838
0.7	0.861

Table 5: Post-hoc Mix LLM-Acc sensitivity to

\delta

. The bold row denotes the value preselected on HotpotQA, not a value selected on Mix. All other hyperparameters are fixed.

$\lambda$	Mix
0.1	0.823
0.3	0.884
0.5	0.846
0.7	0.846
0.9	0.861

Table 6: Post-hoc Mix LLM-Acc sensitivity to

\lambda

. The bold row denotes the value preselected on HotpotQA, not a value selected on Mix. All other hyperparameters are fixed.

$k$	5	6	7	8	9	10
LLM-Acc	0.823	0.853	0.861	0.884	0.869	0.876

Table 7: LLM-Acc under varying top-

k

retrieval count on the 200-question HotpotQA development set. The bold column denotes the selected value. All other hyperparameters are fixed at their defaults.

Figure 3: Pairwise answer-quality win rates of STITCH-RAG against five baselines on HotpotQA, 2Wiki, and Mix, judged by Qwen-Max on comprehensiveness (coverage of relevant details), diversity (variety of useful perspectives), and empowerment (utility for informed judgment). The dashed circle marks the 50% win-rate line. Values outside it favor STITCH-RAG.

Strategy	HotpotQA	2Wiki	Mix
Full-Merge	0.873	0.839	0.807
Semi-Merge	0.895	0.861	0.884
No-Merge	0.879	0.844	0.831

Table 8: LLM-Acc point estimates for one implementation of each merge strategy under a fixed retrieval pipeline. The diagnostic does not evaluate run-level variance, retrieval recall, graph compression, statistical significance, or all possible implementations of the three strategies.

Decay Function	LLM-Acc
$\exp(-\alpha\Delta t)$ (pure exponential)	0.853
$\sigma(-\alpha\Delta t+b)$ (sigmoid gate)	0.815
$\exp(-\tanh(\alpha\Delta t))$ (ours)	0.884

Table 9: LLM-Acc on Mix under three temporal decay functions, with all other pipeline components held fixed (same hypergraph, same PPR initialization, same

\alpha=n_{u}/\bar{n}

Explore similar work

IndexRAG: Index-Time Reasoning for Multi-Hop Retrieval-Augmented Generation
Mar 17, 2026Zhenghua Bao, Yi ShiMulti-Hop Reasoning Question-Answering Benchmarks
Continuum AI Shanghai, China · Continuum AI San Francisco, CA, USA
SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges
Aug 12, 2026Yuchao Wu, Junqin Li, XingCheng Liang +4Graph-Based Retrieval Augmented Generation Knowledge Graphs
Zleap AI
Corpus-Guided Dual-Path Propagation for Graph Retrieval-Augmented Generation
Sep 29, 2026Baoxian Liu, Tong WeiGraph-Based Retrieval Augmented Generation Graph-Based Retrieval
College of Software Engineering, Southeast University, Nanjing 210096, China · Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China · School of Computer Science and Engineering, Southeast University, Nanjing 210096, China

Mar 17, 2026, cs.CLJ/K move · Enter open · S save

IndexRAG: Index-Time Reasoning for Multi-Hop Retrieval-Augmented Generation

Zhenghua Bao, Yi Shi

Continuum AI Shanghai, China · Continuum AI San Francisco, CA, USA

Multi-Hop Reasoning Question-Answering Benchmarks Bridge

Open paper AskPDF arXiv

Multi-hop question answering (QA) requires reasoning across multiple documents, yet existing retrieval-augmented generation (RAG) approaches address this either through graph-based methods requiring additional online processing or iterative multi-step reasoning. We present IndexRAG, a novel approach that shifts cross-document reasoning from online inference to offline indexing. IndexRAG identifies bridge entities shared across documents and generates bridging facts as independently retrievable units, requiring no additional training or fine-tuning. Experiments on three widely-used multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA, MuSiQue) show that IndexRAG improves F1 over Naive RAG by 4.6 points on average, while requiring only single-pass retrieval and a single LLM call at inference time. When combined with IRCoT, IndexRAG achieves the best average performance among all evaluated methods, including graph-based baselines such as HippoRAG2 and FastGraphRAG, while relying on a flat vector index. Our code is available at https://github.com/Continuum-AI-Corp/IndexRAG .

Abstract

Explore similar work

IndexRAG: Index-Time Reasoning for Multi-Hop Retrieval-Augmented Generation

SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges

Corpus-Guided Dual-Path Propagation for Graph Retrieval-Augmented Generation