Graph-based retrieval-augmented generation (GraphRAG) answers questions by retrieving over a knowledge graph built from a corpus. Yet retrieval strategies are designed around the structure their own construction pipeline produces, and whether they survive a change of construction is rarely tested. We study this cross-construction portability: whether one retrieval procedure, with no construction-specific schema, relation names, or retuning, stays effective when the graph is built differently. We introduce ArcRAG, which induces a query-local graph interface at inference time (the node labels, relation descriptors, and property keys reachable from the entities a question names), plans multi-hop traversals against it, and executes and repairs them as Cypher. We build each of the MuSiQue, HotpotQA, and TriviaQA corpora as a schema-guided graph (typed nodes, a closed relation set, source provenance) and as an open-information-extraction graph (untyped nodes, free-text relations), with the retriever's configuration fixed across them. We compare against a construction-agnostic Direct-Cypher agent, ablate each stage across retry and pass budgets on both graph families, and compare with results reported for prior GraphRAG systems, most of which design retrieval together with their own graph construction. Across the two constructions, we find that retrieval need not be co-designed with the graph: query-time interface induction keeps a construction-agnostic retriever effective when the construction changes, although construction still shapes absolute accuracy.
Figures & tables
System
Semantics
Prep.
Interface
Programs
Cross-constr.
GraphRAG ( Edge et al., 2025 )
own
✓
✗
✗
✗
HippoRAG ( Gutiérrez et al., 2025a )
own
✓
✗
✗
∘
HippoRAG 2 ( Gutiérrez et al., 2025b )
own
✓
✗
✗
✗
LightRAG ( Guo et al., 2025 )
own
✓
✗
✗
✗
PathRAG ( Chen et al., 2025 )
own
✓
✗
✗
✗
StepChain GraphRAG ( Ni et al., 2025 )
own
✓
✗
✗
✗
Table 1: Positioning along the portability axis, to our reading of each system’s paper and released implementation. Semantics : where the retriever’s knowledge of node and relation types comes from ( own : fixed by the system’s own construction; curated : a curated KG such as Freebase or Wikidata; prompt : a graph description in the prompt; explored : offline exploration of the target graph; schema : a global schema read from the graph; induced : induced per question at inference time). Prep. : a graph-specific step before questions are answered. Interface : an explicit per-query description of relevant structure passed to later stages. Programs : executes a graph query language. Cross-constr. : the same method evaluated on more than one construction of the same data. ✓ yes, ✗ no, ∘ partial; partial entries are discussed in § 2 .
Figure 1: ArcRAG at inference (left) and the harness (right): exploration → planning → generation → synthesis.
Graph
Corpus
Nodes
Edges
FinReflectKG
MuSiQue
58,418
80,676
HotpotQA
33,203
63,493
TriviaQA
72,266
99,915
HippoRAG OpenIE
MuSiQue
85,520
142,315
HotpotQA
101,200
130,053
TriviaQA
162,687
193,470
Table 2: Graphs produced by the two construction methodologies over the same three corpora.
Function
Fixed in code
Decided by the LLM
Explore
read-only queries; explorer, turn, and depth budget
which relations and paths to follow
Plan
output format; [validation against S^q ]
subplans, hop order, answer type
Acceptable
error, empty result, unbound variable, row cap
[none]
Refine
traversal shape fixed; attempt budget
revised predicates and bindings
Sufficient
iteration cap
whether evidence answers q ; follow-up q′
Table 3: What each function of Algorithm 1 fixes in code and what the LLM decides.
MuSiQue
HotpotQA
TriviaQA
Method
EM
F1
EM
F1
F1
GraphRAG ( Edge et al., 2025 )
27.3
38.5
55.2
68.6
45.1
LightRAG ( Guo et al., 2025 )
20.0
29.3
33.3
44.9
40.2
PathRAG ( Chen et al., 2025 )
8.4
20.8
23.8
41.2
37.4
HippoRAG ( Gutiérrez et al., 2025a )
27.8
40.5
58.5
73.1
—
HippoRAG 2 ( Gutiérrez et al., 2025b )
37.2
48.6
62.7
75.5
46.9
Table 4: Best EM and F1 reported for each method on each dataset, taken across all models and configurations its authors evaluated. Protocols, answer models, and scoring code differ across sources, so this is a best-reported summary rather than a controlled comparison. Prior work reports F1 only on TriviaQA.
MuSiQue
HotpotQA
TriviaQA
Method
EM
F1
EM
F1
F1
HippoRAG
26.2
35.1
52.6
63.5
—
HippoRAG 2
37.2
48.6
62.7
75.5
46.9
ArcRAG (w/ OpenIE Graph)
38.0
45.0
65.5
72.2
71.6
ArcRAG (w/ FinReflectKG)
44.0
53.0
74.5
80.8
87.9
Table 5: Transfer across knowledge-graph families. All ArcRAG prompts, models, and hyperparameters are fixed within a dataset; only the graph family and its provenance-determined evidence store change. HippoRAG and HippoRAG 2 figures for MuSiQue and HotpotQA are as reported by Bai et al. (2025) under a common harness; the HippoRAG 2 TriviaQA figure is from Luo et al. (2026) . As above, prior work reports F1 only on TriviaQA.
Appendix figures & tables10 assets
Supplementary material from the paper’s appendix.
Appendix
Stage
Temp.
Top- p
Thinking
Max tokens
Query refinement
0.0
0.95
off
8,192
Search-phrase extraction
0.0
0.95
off
8,192
Explorer Cypher generation
0.1
0.95
off
8,192
Explorer report synthesis
0.2
0.95
off
8,192
RootPlanner
0.0
0.95
off
8,192
Planner subplan expansion
0.2
0.95
off
8,192
Appendix
Table 6: Sampling parameters by pipeline stage.
Setting
Value
Parallel explorers
2 (anchored-path, topology-path)
Cyphers per explorer
6 (one shot)
Explorer turns
3 (passed; unused on the active subgraph-bound path)
Explorer timeouts
LLM 30 s / Cypher 5 s; report retried once
RootPlanner
2 attempts, 30 s timeout each
Subplan hard cap
4 ( ≥ 1 is a mandatory open-ended neighborhood scan)
Appendix
Table 7: Stage-level settings shared across corpora.
Role
Model
Agents (explorers, planners, generator)
gpt-oss-120b
Query rewrite
gpt-oss-120b
Answer composition and sufficiency judge
Nemotron-3-Super-120B-A12B
Dense embedder
Qwen3-Embedding-0.6B
Sparse retriever
BM25
Appendix
Table 8: Models by pipeline role. Full model identifiers are given in Appendix F ; BM25 uses a server-side IDF modifier, and the embedder its native width.
Knob
MuSiQue
HotpotQA
TriviaQA
Dense prefetch
30
30
30
BM25 prefetch
30
30
30
Top- k fused hits
10
10
10
Appendix
Table 9: Retrieval knobs by corpus. These are the only per-corpus retrieval settings; within a corpus they are identical for both graph families.
Prompt
Tokens
Root planner
3,354
Generator
1,415
Explorer (anchored / topology)
1,377 / 1,197
Node creator
852
Visualize / report / extractor
703 / 536–672 / 449
Appendix
Table 10: Fixed per-call costs (exact, tokenized from the prompts).
Corpus
Graph family
Context tok (mean/p90)
Answer tok (mean)
Total tok/rec
MuSiQue
FinReflectKG
3,282 / 5,940
136
12,085
MuSiQue
OpenIE
5,753 / 15,826
131
9,723
HotpotQA
FinReflectKG
3,637 / 7,618
117
9,924
HotpotQA
OpenIE
2,449 / 5,815
143
6,287
TriviaQA
FinReflectKG
32,632 / 78,394
103
38,815
TriviaQA
OpenIE
4,873 / 12,650
125
8,949
Appendix
Table 11: Persisted-footprint comparison by graph-construction family (same measurements as Table 12 , regrouped by family).
Context tok
Answer
Total
Corpus
Graph
mean
p90
tok
tok/rec
MuSiQue
FinReflectKG
3,282
5,940
136
12,085
OpenIE
5,753
15,826
131
9,723
HotpotQA
FinReflectKG
3,637
7,618
117
9,924
OpenIE
2,449
5,815
143
6,287
TriviaQA
FinReflectKG
32,632
78,394
103
38,815
Appendix
Table 12: Persisted footprint per record, by corpus and graph family. Each run has 1,000 records; the six runs total 85.78M tokens.
FinReflectKG: passes
OpenIE: passes
Configuration
Retries
1
3
5
1
3
5
Generator only
1
12.0
19.0
21.0
6.0
17.0
19.0
3
18.0
35.0
42.0
19.0
39.0
49.0
5
19.0
42.0
50.0
25.0
51.0
59.0
Explorer +
1
27.0
47.0
56.0
32.0
45.0
51.0
Generator
3
34.0
65.0
76.0
41.0
66.0
68.0
Appendix
Table 13: Component ablations on both graph families: EM (%) by configuration, Generator retries per query, and full pipeline passes, on the same stratified sample. Generator only at 1 retry and 1 pass is the Direct-Cypher agent; at larger budgets it is ArcRAG’s Generator without exploration or planning. For each graph family and retry and pass budget, the best configuration is in bold and the lowest in red; at 1 retry and 3 passes on OpenIE, two configurations tie for best.
Figure 2: Accuracy (%) of the three configurations as the retry–pass budget (retries × passes, log scale) grows. Budgets 3, 5, and 15 can each be reached with two settings (e.g. 1 retry × 5 passes or 5 retries × 1 pass); Table 13 reports every setting separately.
Figure 3: Iterative search process with adaptive search breadth.
Retrieval-augmented generation built on knowledge graphs (Graph RAG) outperforms flat passage retrieval on multi-hop question answering by leveraging graph structure. In most existing systems, however, the question only sets the seed nodes; the subsequent traversal becomes "query-blind", depending solely on the graph structure. The exception is QAFD-RAG, which implements query-aware traversal via a flow-diffusion solver with combined edge re-weighting. This architecture requires loading the full graph into Python memory and an iterative solver with a variable number of iterations complicating integration with the graph database. We propose a spreading-activation method that achieves the same query-aware traversal with a single per-step semantic gate: the step weight is the cosine similarity between the candidate entity's description and the question, and the number of iterations is fixed. The whole retrieval procedure - seed mapping, propagation, top-K selection and context assembly - is expressed as a single Cypher query executed in one round-trip to Neo4j; the graph never leaves the database. On MuSiQue our method matches QAFD-RAG by exact match (32.80 vs 33.50) and outperforms the strongest purely-structural baseline in our comparison, HippoRAG, by 5.3 EM and 3.4 F1; on 2WikiMultiHopQA HippoRAG and QAFD-RAG retain an advantage due to their phrase-node architectures. An ablation with the gate disabled confirms that the gate is the source of a simultaneous F1 gain of 3.6 to 7.4 points and a retrieval-latency reduction by a factor of 1.5 to 4.9.
Illia Makarov, Mykola Glybovets
National University of Kyiv-Mohyla Academy Kyiv, Ukraine
Hierarchical Graph Retrieval-Augmented Generation (GraphRAG) organizes corpus knowledge at multiple levels of granularity, yet fixed context construction may fail to translate these multi-resolution representations into a context suited to the current query. We identify this mismatch as the representation--inference gap. We propose Agentic Context Engineering for Hierarchical GraphRAG (ACE-GraphRAG), an inference-time context policy layer that supplements and adapts the initial context for generation. ACE-GraphRAG formulates context construction as a policy over gap-aware refinement, retrieval branches, and task-conditioned adaptation. Parallel Differential Retrieval acquires supplementary evidence from depth-oriented factual and breadth-oriented semantic branches. These evidence increments are consolidated with the initial context while preserving provenance and abstraction levels. Full-ACE applies the full policy uniformly within each task family, whereas Adaptive-ACE selects task- and topology-specific policies for individual queries. We evaluate ACE-GraphRAG on HotpotQA, 2WikiMultiHopQA, and four UltraDomain subsets across multi-hop QA and query-focused summarization. Full-ACE outperforms the evaluated RAG and GraphRAG baselines across both task families, while Adaptive-ACE further improves multi-hop QA and is preferred over Full-ACE on all four UltraDomain subsets. Ablation and topology analyses support treating context construction as a query- and task-dependent inference policy rather than a fixed procedure.
Yongfeng Huang, Yuren Lai, Ruiying Chen +3
CSE, The Chinese University of Hong Kong · Wuhan University of Technology · The Hong Kong University of Science and Technology +1
Retrieval-augmented generation (RAG) improves large language models by incorporating external knowledge without retraining, but existing methods often underuse the relational structure encoded in knowledge graphs. Graph-based RAG can capture entity relationships, yet supervised graph retrieval typically requires labeled question-answer data that may not be available for newly constructed graphs. We address this limitation with SelfGraphRAG, a framework that generates question-answer pairs directly from knowledge graph structure and uses them to train a query-conditioned graph retriever. The generated questions capture multi-hop paths and local neighborhoods, providing relational supervision without manual annotation. Experiments on multi-hop question answering and classification benchmarks show that SelfGraphRAG improves retrieval precision and downstream reasoning performance over embedding-based baselines. These results suggest that knowledge graph structure can provide useful supervision for training graph retrievers when labeled data are unavailable.
Ben Lagnese, Manas Gaur
University of Maryland, Baltimore County (UMBC), Baltimore, MD, USA