Phase D Round 1A v2 — arXiv Baseline Scan¶

掃描時間：2026-06-19 15:25

arXiv 候選數：1000 篇（日期：2023-06-01 → 2026-06-19）

Top N：100（其中 0 篇被 exclude 懲罰後仍進榜）

排序方式（v2）¶

語意相似度（cosine on nomic-embed）再乘上 exclude 三級懲罰係數（取命中的最重一級）：

Tier	命中內容	係數
1 典範衝突	global GraphRAG / community detection / Leiden	×0.3
2 方法論不採用	LoRA・QLoRA・parameter-efficient / continual pretraining	×0.5
3 其他排除	chatbot UI / hiring / careers 等 off-topic	×0.7

各階段狀態：

❌ Stage 4 規則加權（venue tier、citation、recency）
❌ Stage 5 Claude Haiku 評分（R / Q / S 三維度）
❌ Stage 6 Claude Sonnet 深度分析（引用建議、差異化論述）
❌ Stage 7 VPN 下載清單（IEEE/Springer 等付費期刊）

高 similarity ≠ 必然相關（embedding 可能誤判）。請當作 初步篩選，後續會由 Claude 評分修正。

Top 100 候選論文¶

1. OMD-GraphRAG: Enhancing GraphRAG with Ontology-Guided Extraction, Multi-Dimensional Clustering and Dual-Channel Fusion¶

相似度：0.7597
作者：Jie Wang, Honghua Huang, Xi Ge et al.
發表日期：2026-03-26
arXiv：2603.25152
PDF：https://arxiv.org/pdf/2603.25152v3

Retrieval-Augmented Generation (RAG) systems face significant challenges in complex reasoning, multi-hop queries, and domain-specific QA. While existing GraphRAG frameworks have made progress in structural knowledge organization, they still have limitations in knowledge extraction precision, community report integrity, and retrieval performance. This paper proposes OMD-GraphRAG, an enhanced framework built upon open-source GraphRAG. The framework introduces three core innovations: (1) Ontology-G...

2. HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG¶

相似度：0.7595
作者：Yuqi Huang, Ning Liao, Kai Yang et al.
發表日期：2026-02-24
arXiv：2602.20926
PDF：https://arxiv.org/pdf/2602.20926v1

Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations, limiting their reliability in knowledge-intensive tasks. While Retrieval-Augmented Generation (RAG) mitigates these issues, it frequently overlooks structural interdependencies essential for multi-hop reasoning. Graph-based RAG approaches attempt to bridge this gap, yet they typically face trade-offs between accuracy and efficiency due to challenges such as costly graph traversals and semantic nois...

3. STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation¶

相似度：0.7434
作者：Shuai Li, Chen Huang, Duanyu Feng et al.
發表日期：2026-04-11
arXiv：2605.18765
PDF：https://arxiv.org/pdf/2605.18765v1

To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG) leverages lightweight retrievers to efficiently extract information from a given Knowledge Graph (KG). However, existing methods often overlook the inherent challenge of sparse semantic information in graphs. Specifically, our experiments reveal that these methods produce biased retrieval Semantic Shortcut Bias and Long-Tail Path Bias, leading to ...

4. RLM-on-KG: Heuristics First, LLMs When Needed: Adaptive Retrieval Control over Mention Graphs for Scattered Evidence¶

相似度：0.7397
作者：Andrea Volpini, Elie Raad
發表日期：2026-04-18
arXiv：2604.17056
PDF：https://arxiv.org/pdf/2604.17056v1

When does an LLM controller outperform rule-based traversal for knowledge graph exploration? We study this question through RLM-on-KG, a retrieval system that treats an LLM as an autonomous navigator over an RDF-encoded mention graph for grounded question answering. Unlike GraphRAG pipelines that rely on offline LLM indexing, RLM-on-KG performs entity-first, multi-hop exploration at query time using deterministic graph construction and a fixed tool set. Our central finding is a conditional advan...

5. Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems¶

相似度：0.7382
作者：Dongzhe Fan, Zheyi Xue, Siyuan Liu et al.
發表日期：2026-04-01
arXiv：2604.09666
PDF：https://arxiv.org/pdf/2604.09666v1

Retrieval-augmented generation (RAG) and its graph-based extensions (GraphRAG) are effective paradigms for improving large language model (LLM) reasoning by grounding generation in external knowledge. However, most existing RAG and GraphRAG systems operate under static or one-shot retrieval, where a fixed set of documents is provided to the LLM in a single pass. In contrast, recent agentic search systems enable dynamic, multi-round retrieval and sequential decision-making during inference, and h...

6. Beyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAG¶

相似度：0.7378
作者：Jiaming Zhang, Yibo Zhao, Jing Yu et al.
發表日期：2026-05-27
arXiv：2605.28004
PDF：https://arxiv.org/pdf/2605.28004v1

GraphRAG extends retrieval-augmented generation by organizing corpora as explicit knowledge graphs, enabling graph-based retrieval for complex question answering. However, existing frameworks extract entities and relations within individual chunks, leaving cross-chunk relations -- those whose evidence spans multiple passages -- systematically absent from the index. Exhaustive LLM-based recovery of such relations is impractical due to the combinatorial explosion of chunk combinations. We present ...

7. WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora¶

相似度：0.7367
作者：Pengyu Wang, Benfeng Xu, Licheng Zhang et al.
發表日期：2026-02-02
arXiv：2602.02053
PDF：https://arxiv.org/pdf/2602.02053v2

Graph-based Retrieval-Augmented Generation (GraphRAG) organizes external knowledge as a hierarchical graph, enabling efficient retrieval and aggregation of scattered evidence across multiple documents. However, many existing benchmarks for GraphRAG rely on short, curated passages as external knowledge, failing to adequately evaluate systems in realistic settings involving long contexts and large-scale heterogeneous documents. To bridge this gap, we introduce WildGraphBench, a benchmark designed ...

8. GraphRAG on Consumer Hardware: Benchmarking Local LLMs for Healthcare EHR Schema Retrieval¶

相似度：0.7332
作者：Peter Fernandes, Ria Kanjilal
發表日期：2026-05-20
arXiv：2605.20815
PDF：https://arxiv.org/pdf/2605.20815v1

Graph-based Retrieval Augmented Generation (GraphRAG) extends retrieval-augmented generation to support structured reasoning over complex corpora, but its reliability under resource-constrained, privacy-sensitive deployments remains unclear. In healthcare, where Electronic Health Record (EHR) data is complex and strictly regulated, reliance on cloud-based large language models (LLMs) introduces challenges in cost, latency, and compliance. In this work, we present a systematic evaluation of Graph...

9. Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphs¶

相似度：0.7299
作者：Yizhuo Ma, Jinchuan Xu, Tao Wen et al.
發表日期：2026-03-16
arXiv：2603.14828
PDF：https://arxiv.org/pdf/2603.14828v2

Graph Retrieval-Augmented Generation (GraphRAG) has become a common approach for multi-hop reasoning by using knowledge graphs (KGs) as structured retrieval indexes. However, most existing GraphRAG methods implicitly assume that LLM-constructed KGs provide structural support for evidence chaining. In this paper, we show that this assumption does not always hold in practice through an empirical analysis, and identify two recurring KG issue modes often overlooked by current retrievers: spurious no...

10. Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs¶

相似度：0.7284
作者：Su Dong, Qinggang Zhang, Yilin Xiao et al.
發表日期：2026-02-03
arXiv：2602.03578
PDF：https://arxiv.org/pdf/2602.03578v1

Large language models (LLMs) often struggle with knowledge-intensive tasks due to hallucinations and outdated parametric knowledge. While Retrieval-Augmented Generation (RAG) addresses this by integrating external corpora, its effectiveness is limited by fragmented information in unstructured domain documents. Graph-augmented RAG (GraphRAG) emerged to enhance contextual reasoning through structured knowledge graphs, yet paradoxically underperforms vanilla RAG in real-world scenarios, exhibiting ...

11. LiteSemRAG: Lightweight LLM-Free Semantic-Aware Graph Retrieval for Robust RAG¶

相似度：0.7245
作者：Xiao Yue, Guangzhi Qu, Lige Gan
發表日期：2026-03-16
arXiv：2604.16350
PDF：https://arxiv.org/pdf/2604.16350v1

Graph-based Retrieval-Augmented Generation (RAG) has shown great potential for improving multi-level reasoning and structured evidence aggregation. However, existing graph-based RAG frameworks heavily rely on exploiting large language models (LLMs) during indexing and querying, leading to high token consumption, computational cost and latency overhead. In this paper, we propose LiteSemRAG, a lightweight, fully LLM-free, semantic-aware graph retrieval framework. LiteSemRAG constructs a heterogene...

12. LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval¶

相似度：0.7233
作者：He Cheng, Yifu Wu, Saksham Khatwani et al.
發表日期：2026-04-20
arXiv：2604.18913
PDF：https://arxiv.org/pdf/2604.18913v1

Knowledge graphs (KGs) are increasingly integrated with large language models (LLMs) to provide structured, verifiable reasoning. A core operation in this integration is multi-hop retrieval, yet existing systems struggle to balance efficiency, scalability, and interpretability. We introduce LogosKG, a novel, hardware-aligned framework that enables scalable and interpretable k-hop retrieval on large KGs by building on symbolic KG formulations and executing traversal as hardware-efficient operatio...

13. EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval¶

相似度：0.7198
作者：Yifan Song, Xingjian Tao, Zhicheng Yang et al.
發表日期：2026-04-19
arXiv：2604.17458
PDF：https://arxiv.org/pdf/2604.17458v2

Graph-based Retrieval-Augmented Generation (GraphRAG) enhances LLMs by structuring corpus into graphs to facilitate multi-hop reasoning. While recent lightweight approaches reduce indexing costs by leveraging Named Entity Recognition (NER), they rely strictly on structural co-occurrence, failing to capture latent semantic connections between disjoint entities. To address this, we propose EHRAG, a lightweight RAG framework that constructs a hypergraph capturing both structure and semantic level r...

14. BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs¶

相似度：0.7192
作者：Duyi Pan, Tianao Lou, Xin Li et al.
發表日期：2026-03-19
arXiv：2603.20309
PDF：https://arxiv.org/pdf/2603.20309v1

Large Language Models (LLMs) exhibit hallucinations in knowledge-intensive tasks. Graph-based retrieval augmented generation (RAG) has emerged as a promising solution, yet existing approaches suffer from fundamental recall and precision limitations when operating over black-box knowledge graphs -- graphs whose schema and structure are unknown in advance. We identify three core challenges that cause recall loss (semantic instantiation uncertainty and structural path uncertainty) and precision los...

15. N2N-GQA: Noise-to-Narrative for Graph-Based Table-Text Question Answering Using LLMs¶

相似度：0.7189
作者：Mohamed Sharafath, Aravindh Annamalai, Ganesh Murugan et al.
發表日期：2026-01-10
arXiv：2601.06603
PDF：https://arxiv.org/pdf/2601.06603v1

Multi-hop question answering over hybrid table-text data requires retrieving and reasoning across multiple evidence pieces from large corpora, but standard Retrieval-Augmented Generation (RAG) pipelines process documents as flat ranked lists, causing retrieval noise to obscure reasoning chains. We introduce N2N-GQA. To our knowledge, it is the first zeroshot framework for open-domain hybrid table-text QA that constructs dynamic evidence graphs from noisy retrieval outputs. Our key insight is tha...

16. XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation¶

相似度：0.7152
作者：Zhuoling Li, Ha Linh Hong Tran Nguyen, Valeria Bladinieres et al.
發表日期：2026-04-27
arXiv：2604.24623
PDF：https://arxiv.org/pdf/2604.24623v1

Graph-based Retrieval-Augmented Generation (GraphRAG) extends traditional RAG by using knowledge graphs (KGs) to give large language models (LLMs) a structured, semantically coherent context, yielding more grounded answers. However, GraphRAG reasoning process remains a black-box, limiting our ability to understand how specific pieces of structured knowledge influence the final output. Existing explainability (XAI) methods for RAG systems, designed for text-based retrieval, are limited to interpr...

17. GraphRAG for Engineering Diagrams: ChatP&ID Enables LLM Interaction with P&IDs¶

相似度：0.7124
作者：Achmad Anggawirya Alimin, Artur M. Schweidtmann
發表日期：2026-03-23
arXiv：2603.22528
PDF：https://arxiv.org/pdf/2603.22528v1

Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG) and knowledge graphs offer new opportunities for interacting with engineering diagrams such as Piping and Instrumentation Diagrams (P&IDs). However, directly processing raw images or smart P&ID files with LLMs is often costly, inefficient, and prone to hallucinations. This work introduces ChatP&ID, an agentic framework that enables grounded and cost-effective natural-language interaction with P&IDs using Graph Retrie...

18. S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answering¶

相似度：0.7116
作者：Rong Fu, Yemin Wang, Tianxiang Xu et al.
發表日期：2026-03-05
arXiv：2603.23512
PDF：https://arxiv.org/pdf/2603.23512v1

We present S-Path-RAG, a semantic-aware shortest-path Retrieval-Augmented Generation framework designed to improve multi-hop question answering over large knowledge graphs. S-Path-RAG departs from one-shot, text-heavy retrieval by enumerating bounded-length, semantically weighted candidate paths using a hybrid weighted $k$-shortest, beam, and constrained random-walk strategy, learning a differentiable path scorer together with a contrastive path encoder and lightweight verifier, and injecting a ...

19. ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering¶

相似度：0.7112
作者：Yikai Zhu, Kunfeng Chen, Qihuang Zhong et al.
發表日期：2026-05-27
arXiv：2605.28093
PDF：https://arxiv.org/pdf/2605.28093v2

Retrieval-augmented generation (RAG) has emerged as a promising paradigm for enhancing large language models (LLMs) on multi-hop question answering (QA), which requires reasoning over evidence from multiple documents. Current multi-hop RAG methods generally focus on either query-side task decomposition or corpus-side knowledge graph construction. Despite their progress, these methods still struggle to achieve satisfactory performance on complex multi-hop QA tasks. To this end, we propose ConRAG,...

20. Domain-Specific Knowledge Graphs in RAG-Enhanced Healthcare LLMs¶

相似度：0.7106
作者：Sydney Anuyah, Mehedi Mahmud Kaushik, Hao Dai et al.
發表日期：2026-01-21
arXiv：2601.15429
PDF：https://arxiv.org/pdf/2601.15429v1

Large Language Models (LLMs) generate fluent answers but can struggle with trustworthy, domain-specific reasoning. We evaluate whether domain knowledge graphs (KGs) improve Retrieval-Augmented Generation (RAG) for healthcare by constructing three PubMed-derived graphs: $\mathbb{G}_1$ (T2DM), $\mathbb{G}_2$ (Alzheimer's disease), and $\mathbb{G}_3$ (AD+T2DM). We design two probes: Probe 1 targets merged AD T2DM knowledge, while Probe 2 targets the intersection of $\mathbb{G}_1$ and $\mathbb{G}_2$...

21. IndexRAG: Bridging Facts for Cross-Document Reasoning at Index Time¶

相似度：0.7103
作者：Zhenghua Bao, Yi Shi
發表日期：2026-03-17
arXiv：2603.16415
PDF：https://arxiv.org/pdf/2603.16415v1

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 u...

22. StratRAG: A Multi-Hop Retrieval Evaluation Dataset for Retrieval-Augmented Generation Systems¶

相似度：0.7098
作者：Aryan Patodiya
發表日期：2026-03-06
arXiv：2604.22757
PDF：https://arxiv.org/pdf/2604.22757v1

We introduce StratRAG, an open-source retrieval evaluation dataset for benchmarking Retrieval-Augmented Generation (RAG) systems on multi-hop reasoning tasks under realistic, noisy document-pool conditions. Derived from HotpotQA (distractor setting), StratRAG comprises 2,200 examples across three question types -- bridge, comparison, and yes-no -- each paired with a pool of 15 candidate documents containing exactly 2 gold documents and 13 topically related distractors. We benchmark three retriev...

23. A phenotype-driven and evidence-governed framework for knowledge graph enrichment and hypotheses discovery in population data¶

相似度：0.7096
作者：Adela Bâra, Simona-Vasilica Oprea
發表日期：2026-04-18
arXiv：2604.16982
PDF：https://arxiv.org/pdf/2604.16982v1

Current knowledge graph (KG) construction methods are confirmatory, focusing on recovering known relationships rather than identifying novel or context-dependent nodes. This paper proposes a phenotype-driven and evidence-governed framework that shifts the paradigm toward structured hypothesis discovery and controlled KG expansion. The approach integrates graph neural networks (GNNs) for phenotype discovery, causal inference, probabilistic reasoning and large language models (LLMs) for hypothesis...

24. KGiRAG: An Iterative GraphRAG Approach for Responding Sensemaking Queries¶

相似度：0.7094
作者：Isabela Iacob, Melisa Marian, Gheorghe Cosmin Silaghi
發表日期：2026-03-02
arXiv：2604.20859
PDF：https://arxiv.org/pdf/2604.20859v1

Recent literature highlights the potential of graph-based approaches within large language model (LLM) retrieval-augmented generation (RAG) pipelines for answering queries of varying complexity, particularly those that fall outside the LLM's prior knowledge. However, LLMs are prone to hallucination and often face technical limitations in handling contexts large enough to ground complex queries effectively. To address these challenges, we propose a novel iterative, feedback-driven GraphRAG archit...

25. A Human-in-the-Loop, LLM-Centered Architecture for Knowledge-Graph Question Answering¶

相似度：0.7093
作者：Larissa Pusch, Alexandre Courtiol, Tim Conrad
發表日期：2026-02-05
arXiv：2602.05512
PDF：https://arxiv.org/pdf/2602.05512v2

Large Language Models (LLMs) excel at language understanding but remain limited in knowledge-intensive domains due to hallucinations, outdated information, and limited explainability. Text-based retrieval-augmented generation (RAG) helps ground model outputs in external sources but struggles with multi-hop reasoning. Knowledge Graphs (KGs), in contrast, support precise, explainable querying, yet require a knowledge of query languages. This work introduces an interactive framework in which LLMs g...

26. SAGE: Structure Aware Graph Expansion for Retrieval of Heterogeneous Data¶

相似度：0.7085
作者：Prasham Titiya, Rohit Khoja, Tomer Wolfson et al.
發表日期：2026-02-18
arXiv：2602.16964
PDF：https://arxiv.org/pdf/2602.16964v1

Retrieval-augmented question answering over heterogeneous corpora requires connected evidence across text, tables, and graph nodes. While entity-level knowledge graphs support structured access, they are costly to construct and maintain, and inefficient to traverse at query time. In contrast, standard retriever-reader pipelines use flat similarity search over independently chunked text, missing multi-hop evidence chains across modalities. We propose SAGE (Structure Aware Graph Expansion) framewo...

27. TechRAG: Evidence-Gated Multimodal Agentic RAG for Technical Literature Reasoning¶

相似度：0.7080
作者：Kanwar Bharat Singh
發表日期：2026-06-01
arXiv：2606.01613
PDF：https://arxiv.org/pdf/2606.01613v2

This paper presents an agentic multimodal retrieval-augmented generation (RAG) framework for domain-specific literature reasoning, instantiated on a curated corpus of several thousand papers in intelligent tires, vehicle dynamics, vehicle control, sensing, estimation, and machine learning. Unlike conventional single-pass RAG systems, the proposed architecture uses an autonomous, evidence-gated pipeline that classifies query intent, generates separate text and visual query rewrites, performs hybr...

28. Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs¶

相似度：0.7071
作者：Yoav Kor Sade, Arvindh Arun, Rishi Puri et al.
發表日期：2026-05-21
arXiv：2605.21994
PDF：https://arxiv.org/pdf/2605.21994v1

GraphRAG conditions language models on subgraphs retrieved from knowledge graphs, encoded via message-passing GNNs. Because these encoders entangle node contributions through iterated neighborhood aggregation, there is no closed-form way to determine how much each retrieved entity influenced the encoder's output, and therefore no way to faithfully audit what structural evidence actually reached the model. We introduce Ex-GraphRAG, which replaces the GNN encoder with a Multivariate Graph Neural A...

29. ContextRAG: Extraction-Free Hierarchical Graph Construction for Retrieval-Augmented Generation¶

相似度：0.7067
作者：Roman Prosvirnin, Sergei Kuznetsov, Seungmin Jin
發表日期：2026-05-19
arXiv：2605.19735
PDF：https://arxiv.org/pdf/2605.19735v1

Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions, but many current systems rely on large language models (LLMs) to extract entities, relations, and summaries during indexing. These calls add token and wall-clock costs that grow with corpus size. We present ContextRAG, a graph RAG system whose graph topology is constructed without LLM-based entity or relation extraction. ContextRAG derives a fuzzy concept graph over chunk embeddings u...

30. LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems¶

相似度：0.7051
作者：Arijit Khan, Longxu Sun, Xin Huang
發表日期：2026-06-10
arXiv：2606.11560
PDF：https://arxiv.org/pdf/2606.11560v1

Large Language Models (LLMs) have advanced rapidly, but their limitations in structured and multi-hop reasoning underscore the need for graph-native, synergistic artificial intelligence (AI) systems. Graph-structured data underpins critical applications across social, biological, financial, transportation, web, and knowledge domains, making it essential to understand how LLMs can leverage graph computation for grounded, context-rich inference. Three complementary synergies are emerging: LLMs aug...

31. SCOUT-RAG: Scalable and Cost-Efficient Unifying Traversal for Agentic Graph-RAG over Distributed Domains¶

相似度：0.7051
作者：Longkun Li, Yuanben Zou, Jinghan Wu et al.
發表日期：2026-02-09
arXiv：2602.08400
PDF：https://arxiv.org/pdf/2602.08400v1

Graph-RAG improves LLM reasoning using structured knowledge, yet conventional designs rely on a centralized knowledge graph. In distributed and access-restricted settings (e.g., hospitals or multinational organizations), retrieval must select relevant domains and appropriate traversal depth without global graph visibility or exhaustive querying. To address this challenge, we introduce \textbf{SCOUT-RAG} (\textit{\underline{S}calable and \underline{CO}st-efficient \underline{U}nifying \underline{...

32. From Flat to Structural: Enhancing Automated Short Answer Grading with GraphRAG¶

相似度：0.7049
作者：Yucheng Chu, Haoyu Han, Shen Dong et al.
發表日期：2026-02-28
arXiv：2603.19276
PDF：https://arxiv.org/pdf/2603.19276v1

Automated short answer grading (ASAG) is critical for scaling educational assessment, yet large language models (LLMs) often struggle with hallucinations and strict rubric adherence due to their reliance on generalized pre-training. While Rretrieval-Augmented Generation (RAG) mitigates these issues, standard "flat" vector retrieval mechanisms treat knowledge as isolated fragments, failing to capture the structural relationships and multi-hop reasoning essential for complex educational content. T...

33. Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systems¶

相似度：0.7041
作者：Shuhua Yang, Jiahao Zhang, Yilong Wang et al.
發表日期：2026-01-21
arXiv：2601.14662
PDF：https://arxiv.org/pdf/2601.14662v2

Graph-based retrieval-augmented generation (GraphRAG) systems construct knowledge graphs over document collections to support multi-hop reasoning. While prior work shows that GraphRAG responses may leak retrieved subgraphs, the feasibility of query-efficient reconstruction of the hidden graph structure remains unexplored under realistic query budgets. We study a budget-constrained black-box setting where an adversary adaptively queries the system to steal its latent entity-relation graph. We pro...

34. BridgeRAG: Training-Free Bridge-Conditioned Retrieval for Multi-Hop Question Answering¶

相似度：0.7039
作者：Andre Bacellar
發表日期：2026-04-03
arXiv：2604.03384
PDF：https://arxiv.org/pdf/2604.03384v2

Multi-hop retrieval is not a single-step relevance problem: later-hop evidence should be ranked by its utility conditioned on retrieved bridge evidence, not by similarity to the original query alone. We present BridgeRAG, a training-free, graph-free retrieval method for retrieval-augmented generation (RAG) over multi-hop questions that operationalizes this view with a tripartite scorer s(q,b,c) over (question, bridge, candidate). BridgeRAG separates coverage from scoring: dual-entity ANN expansi...

35. Relink: Constructing Query-Driven Evidence Graph On-the-Fly for GraphRAG¶

相似度：0.7035
作者：Manzong Huang, Chenyang Bu, Yi He et al.
發表日期：2026-01-12
arXiv：2601.07192
PDF：https://arxiv.org/pdf/2601.07192v1

Graph-based Retrieval-Augmented Generation (GraphRAG) mitigates hallucinations in Large Language Models (LLMs) by grounding them in structured knowledge. However, current GraphRAG methods are constrained by a prevailing \textit{build-then-reason} paradigm, which relies on a static, pre-constructed Knowledge Graph (KG). This paradigm faces two critical challenges. First, the KG's inherent incompleteness often breaks reasoning paths. Second, the graph's low signal-to-noise ratio introduces distrac...

36. UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG¶

相似度：0.7022
作者：Dobrik Georgiev, Kheeran Naidu, Alberto Cattaneo et al.
發表日期：2026-01-28
arXiv：2603.28773
PDF：https://arxiv.org/pdf/2603.28773v1

Large language models (LLMs) frequently generate confident yet factually incorrect content when used for language generation (a phenomenon often known as hallucination). Retrieval augmented generation (RAG) tries to reduce factual errors by identifying information in a knowledge corpus and putting it in the context window of the model. While this approach is well-established for document-structured data, it is non-trivial to adapt it for Knowledge Graphs (KGs), especially for queries that requir...

37. RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering¶

相似度：0.7017
作者：Kaehyun Um, KyuHwan Yeom, Haerim Yang et al.
發表日期：2026-01-27
arXiv：2601.19225
PDF：https://arxiv.org/pdf/2601.19225v2

Large Language Models (LLMs) have recently demonstrated remarkable reasoning abilities, yet hallucinate on knowledge-intensive tasks. Retrieval-augmented generation (RAG) mitigates this issue by grounding answers in external sources, e.g., knowledge graphs (KGs). However, existing KG-based RAG approaches rely on semantics-unaware path sampling and are weakly aligned with KG reasoning objectives, which limits further accuracy gains. They also feed retrieved paths directly into the reasoner withou...

38. FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow¶

相似度：0.7017
作者：Bihao Zhan, Zongsheng Cao, Jie Zhou et al.
發表日期：2026-06-16
arXiv：2606.17856
PDF：https://arxiv.org/pdf/2606.17856v1

Graph-based retrieval-augmented generation (GraphRAG) is effective for knowledge-intensive and multi-hop query tasks; however, many existing methods primarily seed entity-based graphs and rely on implicit semantic relevance propagation. This often (i) under-retrieves when user queries are abstract and semantically sparse at the entity level, and (ii) suffers from brittle multi-hop reasoning, where noisy activations can derail entity-to-entity transitions and corrupt the inferred relation chain, ...

39. STEM: Structure-Tracing Evidence Mining for Knowledge Graphs-Driven Retrieval-Augmented Generation¶

相似度：0.7014
作者：Peng Yu, En Xu, Bin Chen et al.
發表日期：2026-04-24
arXiv：2604.22282
PDF：https://arxiv.org/pdf/2604.22282v2

Knowledge Graph-based Question Answering (KGQA) plays a pivotal role in complex reasoning tasks but remains constrained by two persistent challenges: the structural heterogeneity of Knowledge Graphs(KGs) often leads to semantic mismatch during retrieval, while existing reasoning path retrieval methods lack a global structural perspective. To address these issues, we propose Structure-Tracing Evidence Mining (STEM), a novel framework that reframes multi-hop reasoning as a schema-guided graph sear...

40. PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents¶

相似度：0.7011
作者：Mikhail Menschikov, Matvey Iskornev, Alexander Kharitonov et al.
發表日期：2026-05-13
arXiv：2605.13481
PDF：https://arxiv.org/pdf/2605.13481v1

We introduce PersonalAI 2.0 (PAI-2), a novel framework, designed to enhance large language model (LLM) based systems through integration of external knowledge graphs (KG). The proposed approach addresses key limitations of existing Graph Retrieval-Augmented Generation (GraphRAG) methods by incorporating a dynamic, multistage query processing pipeline. The central point of PAI-2 design is its ability to perform adaptive, iterative information search, guided by extracted entities, matched graph ve...

41. HyperRAG: Reasoning N-ary Facts over Hypergraphs for Retrieval Augmented Generation¶

相似度：0.7009
作者：Wen-Sheng Lien, Yu-Kai Chan, Hao-Lung Hsiao et al.
發表日期：2026-02-16
arXiv：2602.14470
PDF：https://arxiv.org/pdf/2602.14470v1

Graph-based retrieval-augmented generation (RAG) methods, typically built on knowledge graphs (KGs) with binary relational facts, have shown promise in multi-hop open-domain QA. However, their rigid retrieval schemes and dense similarity search often introduce irrelevant context, increase computational overhead, and limit relational expressiveness. In contrast, n-ary hypergraphs encode higher-order relational facts that capture richer inter-entity dependencies and enable shallower, more efficien...

42. Position: How can Graphs Help Large Language Models?¶

相似度：0.6996
作者：Xiyuan Wang, Yi Hu, Yanbo Wang et al.
發表日期：2026-05-04
arXiv：2605.02452
PDF：https://arxiv.org/pdf/2605.02452v1

With the rapid advancement of large language models (LLMs), classic graph learning tasks have greatly benefited from LLMs, including improved encoding of textual features, more efficient construction of graphs from text, and enhanced reasoning over knowledge graphs. In this paper, we ask a complementary question: How can graphs help LLMs? We address this question from three perspectives: 1) graphs provide an up-to-date knowledge source that helps reduce LLM hallucinations, 2) graph-based prompti...

43. MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation¶

相似度：0.6990
作者：Chuanjie Wu, Zhishang Xiang, Yunbo Tang et al.
發表日期：2026-05-30
arXiv：2606.00610
PDF：https://arxiv.org/pdf/2606.00610v1

Retrieval-Augmented Generation (RAG) has become an essential method for mitigating hallucinations in Large Language Models (LLMs) by leveraging external knowledge. Although effective for simple queries, traditional RAG struggles with large-scale, unstructured corpora where information is highly fragmented. Graph-based RAG (GraphRAG) incorporates knowledge graphs to capture structural relationships, enabling more comprehensive retrieval for complex reasoning. However, existing GraphRAG methods re...

44. Agentic GraphRAG: Navigating Unstructured Financial Data with Collaborative AI¶

相似度：0.6984
作者：Arthur Capozzi, Dirk Helbing
發表日期：2026-04-15
arXiv：2605.18770
PDF：https://arxiv.org/pdf/2605.18770v1

We present a collaborative agentic GraphRAG framework for expert analysis of commercial registry data. Public registries are often formally accessible, yet difficult to use in practice because they combine structured records with large volumes of unstructured legal text. This limits conventional keyword and vector-only retrieval, especially for multi-hop, temporal, and entity-centric investigations. Our approach builds a Neo4j knowledge graph through a three-phase pipeline: (i) deterministic ing...

45. Large Language Models Meet Biomedical Knowledge Graphs for Mechanistically Grounded Therapeutic Prioritization¶

相似度：0.6984
作者：Chih-Hsuan Wei, Chi-Ping Day, Zhizheng Wang et al.
發表日期：2026-04-17
arXiv：2604.19815
PDF：https://arxiv.org/pdf/2604.19815v1

Drug repurposing is often framed as a candidate identification task, but existing approaches provide limited guidance for distinguishing biologically plausible candidates from historically well-connected ones. Here we introduce DrugKLM, a hybrid framework that integrates biomedical knowledge graph structure with large language model-based mechanistic reasoning to enable mechanistically grounded therapeutic prioritization. Across benchmark datasets, DrugKLM outperforms knowledge graph-only and la...

46. Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering¶

相似度：0.6982
作者：Rezarta Islamaj, Joey Chan, Robert Leaman et al.
發表日期：2026-05-12
arXiv：2605.12313
PDF：https://arxiv.org/pdf/2605.12313v1

Multi-hop question answering (QA) remains a significant challenge in the biomedical domain, requiring systems to integrate information across multiple sources to answer complex questions. To address this problem, the BioCreative IX MedHopQA shared task was designed to benchmark in multi-hop reasoning for large language models (LLMs). We developed a novel dataset of 1,000 challenging QA pairs spanning diseases, genes, and chemicals, with particular emphasis on rare diseases. Each question was con...

47. Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge Graphs¶

相似度：0.6981
作者：Hang Gao, Dimitris N. Metaxas
發表日期：2026-03-14
arXiv：2603.14006
PDF：https://arxiv.org/pdf/2603.14006v1

GraphRAG is increasingly adopted for converting unstructured corpora into graph structures to enable multi-hop reasoning. However, standard graph algorithms rely heavily on static connectivity and explicit edges, often failing in real-world scenarios where knowledge graphs (KGs) are noisy, sparse, or incomplete. To address this limitation, we introduce INSES (Intelligent Navigation and Similarity Enhanced Search), a dynamic framework designed to reason beyond explicit edges. INSES couples LLM-gu...

48. Incorporating contextual information into KGWAS for interpretable GWAS discovery¶

相似度：0.6974
作者：Cheng Jiang, Brady Ryan, Megan Crow et al.
發表日期：2026-03-26
arXiv：2603.25855
PDF：https://arxiv.org/pdf/2603.25855v1

Genome-Wide Association Studies (GWAS) identify associations between genetic variants and disease; however, moving beyond associations to causal mechanisms is critical for therapeutic target prioritization. The recently proposed Knowledge Graph GWAS (KGWAS) framework addresses this challenge by linking genetic variants to downstream gene-gene interactions via a knowledge graph (KG), thereby improving detection power and providing mechanistic insights. However, the original KGWAS implementation r...

49. The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QA¶

相似度：0.6969
作者：Yasaman Zarrinkia, Venkatesh Srinivasan, Alex Thomo
發表日期：2026-03-14
arXiv：2603.14045
PDF：https://arxiv.org/pdf/2603.14045v2

Graph-RAG systems achieve strong multi-hop question answering by indexing documents into knowledge graphs, but strong retrieval does not guarantee strong answers. Evaluating KET-RAG, a leading Graph-RAG system, on three multi-hop QA benchmarks (HotpotQA, MuSiQue, 2WikiMultiHopQA), we find that 77% to 91% of questions have the gold answer in the retrieved context, yet accuracy is only 35% to 78%, and 73% to 84% of errors are reasoning failures. We propose two augmentations: (i) SPARQL chain-of-th...

50. GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation¶

相似度：0.6967
作者：Ruizhong Miao, Yuying Wang, Rongguang Wang et al.
發表日期：2026-03-26
arXiv：2603.24925
PDF：https://arxiv.org/pdf/2603.24925v2

Retrieval-augmented generation (RAG) systems that rely on semantic search often fail to retrieve the complete set of evidence for complex queries, particularly when information is distributed across multiple sources. Existing approaches either rely on iterative agentic retrieval, which can be inefficient, or maintain additional structures such as knowledge graphs, which introduce storage and maintenance overhead. In this paper, we propose GraphER, a graph-based enrichment and reranking framework...

51. SCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question Answering¶

相似度：0.6965
作者：Jiujiu Chen, Yazheng Liu, Sihong Xie et al.
發表日期：2026-05-04
arXiv：2605.02819
PDF：https://arxiv.org/pdf/2605.02819v1

Large language models excel at complex reasoning, yet evaluating their intermediate steps remains challenging. Although process reward models provide step-wise supervision, they often suffer from a risk compensation effect, where incorrect steps are offset by later correct ones, assigning high rewards to flawed reasoning paths. This issue is further exacerbated in knowledge graph (KG) reasoning, as there may exist multiple paths between the start and end entities in the KGs, and a risky step can...

52. SRAG: RAG with Structured Data Improves Vector Retrieval¶

相似度：0.6963
作者：Shalin Shah, Srikanth Ryali, Ramasubbu Venkatesh
發表日期：2026-01-27
arXiv：2603.26670
PDF：https://arxiv.org/pdf/2603.26670v1

Retrieval Augmented Generation (RAG) provides the necessary informational grounding to LLMs in the form of chunks retrieved from a vector database or through web search. RAG could also use knowledge graph triples as a means of providing factual information to an LLM. However, the retrieval is only based on representational similarity between a question and the contents. The performance of RAG depends on the numeric vector representations of the query and the chunks. To improve these representati...

53. Retrieving Minimal and Sufficient Reasoning Subgraphs with Graph Foundation Models for Path-aware GraphRAG¶

相似度：0.6963
作者：Haonan Yuan, Qingyun Sun, Junhua Shi et al.
發表日期：2026-03-07
arXiv：2603.07179
PDF：https://arxiv.org/pdf/2603.07179v1

Graph-based retrieval-augmented generation (GraphRAG) exploits structured knowledge to support knowledge-intensive reasoning. However, most existing methods treat graphs as intermediate artifacts, and the few subgraph-based retrieval methods depend on heuristic rules coupled with domain-specific distributions. They fail in typical cold-start scenarios where data in target domains is scarce, thus yielding reasoning contexts that are either informationally incomplete or structurally redundant. In ...

54. Bounded Path Context: A Controlled Study of Visible Path History in LLM-Based Knowledge Graph Question Answering¶

相似度：0.6962
作者：Xihang Shan, Ye Luo
發表日期：2026-05-26
arXiv：2605.26645
PDF：https://arxiv.org/pdf/2605.26645v1

LLM-based knowledge-graph question answering (KGQA) delegates graph traversal to language models, turning each question into a sequence of local relation-selection decisions repeated across beams and hops. A common but untested default is to serialize the complete partial path into every routing prompt, even though the controller already maintains this path as exact symbolic state. Bounded Path Context (BPC) decouples these two roles: the controller retains full paths in symbolic memory for answ...

55. HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG¶

相似度：0.6960
作者：Jinyoung Park, Sanghyeok Lee, Omar Zia Khan et al.
發表日期：2026-01-25
arXiv：2601.17755
PDF：https://arxiv.org/pdf/2601.17755v2

Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform complex reasoning beyond text-chunk retrieval. Recent advances have integrated reinforcement learning (RL) into agentic GraphRAG approaches, enabling iterative interactions with knowledge graphs during training. However, existing RL-based methods suffer from two key limitations: (1)...

56. Pruning Minimal Reasoning Graphs for Efficient Retrieval-Augmented Generation¶

相似度：0.6957
作者：Ning Wang, Kuanyan Zhu, Daniel Yuehwoon Yee et al.
發表日期：2026-02-04
arXiv：2602.04926
PDF：https://arxiv.org/pdf/2602.04926v1

Retrieval-augmented generation (RAG) is now standard for knowledge-intensive LLM tasks, but most systems still treat every query as fresh, repeatedly re-retrieving long passages and re-reasoning from scratch, inflating tokens, latency, and cost. We present AutoPrunedRetriever, a graph-style RAG system that persists the minimal reasoning subgraph built for earlier questions and incrementally extends it for later ones. AutoPrunedRetriever stores entities and relations in a compact, ID-indexed code...

57. Deep GraphRAG: A Balanced Approach to Hierarchical Retrieval and Adaptive Integration¶

相似度：0.6956
作者：Yuejie Li, Ke Yang, Tao Wang et al.
發表日期：2026-01-16
arXiv：2601.11144
PDF：https://arxiv.org/pdf/2601.11144v3

Graph-based Retrieval-Augmented Generation (GraphRAG) frameworks face a trade-off between the comprehensiveness of global search and the efficiency of local search. Existing methods are often challenged by navigating large-scale hierarchical graphs, optimizing retrieval paths, and balancing exploration-exploitation dynamics, frequently lacking robust multi-stage re-ranking. To overcome these deficits, we propose Deep GraphRAG, a framework designed for a balanced approach to hierarchical retrieva...

58. A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning¶

相似度：0.6938
作者：Jiate Liu, Zebin Chen, Shaobo Qiao et al.
發表日期：2026-01-29
arXiv：2601.21162
PDF：https://arxiv.org/pdf/2601.21162v2

Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure. However, practical deployments face two persistent bottlenecks: (i) mixed-difficulty workloads where one-size-fits-all retrieval either wastes cost on easy queries or fails on hard multihop cases, and (ii) extraction loss, where graph abstraction omits fine-grained qualifiers that remain only in source text. We presen...

59. KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation¶

相似度：0.6926
作者：Qizhi Chen, Chao Qi, Yihong Huang et al.
發表日期：2026-03-12
arXiv：2603.11501
PDF：https://arxiv.org/pdf/2603.11501v2

Graph-based Retrieval-Augmented Generation (GraphRAG) constructs the Knowledge Graph (KG) from external databases to enhance the timeliness and accuracy of Large Language Model (LLM) generations. However, this reliance on external data introduces new attack surfaces. Attackers can inject poisoned texts into databases to manipulate LLMs into producing harmful target responses for attacker-chosen queries. Existing research primarily focuses on attacking conventional RAG systems. However, such meth...

60. Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP¶

相似度：0.6918
作者：Martin Vogel, Falk Meyer-Eschenbach, Severin Kohler et al.
發表日期：2026-03-28
arXiv：2603.27277
PDF：https://arxiv.org/pdf/2603.27277v1

Large Language Model (LLM) coding agents typically explore codebases through repeated file-reading and grep-searching, consuming thousands of tokens per query without structural understanding. We present Codebase-Memory, an open-source system that constructs a persistent, Tree-Sitter-based knowledge graph via the Model Context Protocol (MCP), parsing 66 languages through a multi-phase pipeline with parallel worker pools, call-graph traversal, impact analysis, and community discovery. Evaluated a...

61. Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework¶

相似度：0.6913
作者：Komal Kumar, Aman Chadha, Salman Khan et al.
發表日期：2026-04-07
arXiv：2604.06170
PDF：https://arxiv.org/pdf/2604.06170v1

The rapid growth of scientific literature has made it increasingly difficult for researchers to efficiently discover, evaluate, and synthesize relevant work. Recent advances in multi-agent large language models (LLMs) have demonstrated strong potential for understanding user intent and are being trained to utilize various tools. In this paper, we introduce Paper Circle, a multi-agent research discovery and analysis system designed to reduce the effort required to find, assess, organize, and unde...

62. MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering¶

相似度：0.6913
作者：Rezarta Islamaj, Robert Leaman, Joey Chan et al.
發表日期：2026-05-12
arXiv：2605.12361
PDF：https://arxiv.org/pdf/2605.12361v1

Evaluating large language models (LLMs) in the biomedical domain requires benchmarks that can distinguish reasoning from pattern matching and remain discriminative as model capabilities improve. Existing biomedical question answering (QA) benchmarks are limited in this respect. Multiple-choice formats can allow models to succeed through answer elimination rather than inference, while widely circulated exam-style datasets are increasingly vulnerable to performance saturation and training data con...

63. TIEG-Youpu Solution for NeurIPS 2022 WikiKG90Mv2-LSC¶

相似度：0.6908
作者：Feng Nie, Zhixiu Ye, Sifa Xie et al.
發表日期：2026-03-30
arXiv：2603.28512
PDF：https://arxiv.org/pdf/2603.28512v1

WikiKG90Mv2 in NeurIPS 2022 is a large encyclopedic knowledge graph. Embedding knowledge graphs into continuous vector spaces is important for many practical applications, such as knowledge acquisition, question answering, and recommendation systems. Compared to existing knowledge graphs, WikiKG90Mv2 is a large scale knowledge graph, which is composed of more than 90 millions of entities. Both efficiency and accuracy should be considered when building graph embedding models for knowledge graph a...

64. Plasma GraphRAG: Physics-Grounded Parameter Selection for Gyrokinetic Simulations¶

相似度：0.6904
作者：Ruichen Zhang, Feda AlMuhisen, Chenguang Wan et al.
發表日期：2026-04-07
arXiv：2604.06279
PDF：https://arxiv.org/pdf/2604.06279v1

Accurate parameter selection is fundamental to gyrokinetic plasma simulations, yet current practices rely heavily on manual literature reviews, leading to inefficiencies and inconsistencies. We introduce Plasma GraphRAG, a novel framework that integrates Graph Retrieval-Augmented Generation (GraphRAG) with large language models (LLMs) for automated, physics-grounded parameter range identification. By constructing a domain-specific knowledge graph from curated plasma literature and enabling struc...

65. Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database¶

相似度：0.6900
作者：Madhulatha Mandarapu, Sandeep Kunkunuru
發表日期：2026-03-16
arXiv：2603.15080
PDF：https://arxiv.org/pdf/2603.15080v3

Biomedical knowledge is fragmented across siloed databases -- Reactome for pathways, STRING for protein interactions, ClinicalTrials.gov for study registries, DrugBank for drug vocabularies, DGIdb for drug-gene interactions, SIDER for side effects. We present three open-source biomedical knowledge graphs -- Pathways KG (118,686 nodes, 834,785 edges from 5 sources), Clinical Trials KG (7,774,446 nodes, 26,973,997 edges from 5 sources), and Drug Interactions KG (32,726 nodes, 191,970 edges from 3 ...

66. KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration¶

相似度：0.6900
作者：Mohammad Amanlou, Erfan Shafiee Moghaddam, Yasaman Amou Jafari et al.
發表日期：2026-02-23
arXiv：2602.20135
PDF：https://arxiv.org/pdf/2602.20135v1

With the rise of large language models (LLMs), they have become instrumental in applications such as Retrieval-Augmented Generation (RAG). Yet evaluating these systems remains bottlenecked by the time and cost of building specialized assessment datasets. We introduce KNIGHT, an LLM-based, knowledge-graph-driven framework for generating multiple-choice question (MCQ) datasets from external sources. KNIGHT constructs a topic-specific knowledge graph, a structured and parsimonious summary of entiti...

67. Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis¶

相似度：0.6897
作者：Hazem Amamou, Stéphane Gagnon, Alan Davoust et al.
發表日期：2026-03-05
arXiv：2603.05698
PDF：https://arxiv.org/pdf/2603.05698v2

Retrieval-Augmented Generation (RAG) was introduced to enhance the capabilities of Large Language Models (LLMs) beyond their encoded prior knowledge. This is achieved by providing LLMs with an external source of knowledge, which helps reduce factual hallucinations and enables access to new information not available during pretraining. However, inconsistent retrieved information can negatively affect LLM responses. The Retrieval-Augmented Generation Benchmark (RGB) was introduced to evaluate the ...

68. Enhancing Metacognitive AI: Knowledge-Graph Population with Graph-Theoretic LLM Enrichment¶

相似度：0.6897
作者：Deniz Askin, Gal Hadar, Brendan Conway-Smith
發表日期：2026-05-15
arXiv：2605.16676
PDF：https://arxiv.org/pdf/2605.16676v1

Metacognition-the ability to monitor one's own knowledge state, spot gaps, and autonomously fill them--remains largely absent from modern AI. Here, we present MetaKGEnrich, a fully automated pipeline that endows large language model (LLM) applications with self-directed knowledge repair. The system (i) builds knowledge graphs from a seed query, (ii) detects sparse regions via seven graph metrics, (iii) has GPT-4o generate targeted questions, (iv) retrieves web evidence with Tavily and ingests it...

69. GROUNDEDKG-RAG: Grounded Knowledge Graph Index for Long-document Question Answering¶

相似度：0.6895
作者：Tianyi Zhang, Andreas Marfurt
發表日期：2026-04-06
arXiv：2604.04359
PDF：https://arxiv.org/pdf/2604.04359v1

Retrieval-augmented generation (RAG) systems have been widely adopted in contemporary large language models (LLMs) due to their ability to improve generation quality while reducing the required input context length. In this work, we focus on RAG systems for long-document question answering. Current approaches suffer from a heavy reliance on LLM descriptions resulting in high resource consumption and latency, repetitive content across hierarchical levels, and hallucinations due to no or limited g...

70. GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning¶

相似度：0.6893
作者：Yuchen Ying, Weiqi Jiang, Tongya Zheng et al.
發表日期：2026-03-02
arXiv：2603.01410
PDF：https://arxiv.org/pdf/2603.01410v2

Knowledge graphs provide structured and reliable information for many real-world applications, motivating increasing interest in combining large language models (LLMs) with graph-based retrieval to improve factual grounding. Recent Graph-based Retrieval-Augmented Generation (GraphRAG) methods therefore introduce iterative interaction between LLMs and knowledge graphs to enhance reasoning capability. However, existing approaches typically depend on manually designed guidance and interact with kno...

71. GAAMA: Graph Augmented Associative Memory for Agents¶

相似度：0.6892
作者：Swarna Kamal Paul, Shubhendu Sharma, Nitin Sareen
發表日期：2026-03-29
arXiv：2603.27910
PDF：https://arxiv.org/pdf/2603.27910v2

AI agents that interact with users across multiple sessions require persistent long-term memory to maintain coherent, personalized behavior. Current approaches either rely on flat retrieval-augmented generation (RAG), which loses structural relationships among memories, or use entity-centric knowledge graphs that suffer from mega-hub effects in conversational data, diluting graph-based relevance propagation. We propose GAAMA, a graph-augmented associative memory for agents that constructs a conc...

72. Frugal Knowledge Graph Construction with Local LLMs: A Zero-Shot Pipeline, Self-Consistency and Wisdom of Artificial Crowds¶

相似度：0.6887
作者：Pierre Jourlin
發表日期：2026-04-13
arXiv：2604.11104
PDF：https://arxiv.org/pdf/2604.11104v1

This paper presents an empirical study of a multi-model zero-shot pipeline for knowledge graph construction and exploitation, executed entirely through local inference on consumer-grade hardware. We propose a reproducible evaluation framework integrating two external benchmarks (DocRED, HotpotQA), WebQuestionsSP-style synthetic data, and the RAGAS evaluation framework in an automated pipeline. On 500 document-level relations, our system achieves an F1 of 0.70 $\pm$ 0.041 in zero-shot, compared t...

73. Mixture of Demonstrations for Textual Graph Understanding and Question Answering¶

相似度：0.6883
作者：Yukun Wu, Lihui Liu
發表日期：2026-03-23
arXiv：2603.23554
PDF：https://arxiv.org/pdf/2603.23554v1

Textual graph-based retrieval-augmented generation (GraphRAG) has emerged as a powerful paradigm for enhancing large language models (LLMs) in domain-specific question answering. While existing approaches primarily focus on zero-shot GraphRAG, selecting high-quality demonstrations is crucial for improving reasoning and answer accuracy. Furthermore, recent studies have shown that retrieved subgraphs often contain irrelevant information, which can degrade reasoning performance. In this paper, we p...

74. LEC-KG: An LLM-Embedding Collaborative Framework for Domain-Specific Knowledge Graph Construction -- A Case Study on SDGs¶

相似度：0.6876
作者：Yikai Zeng, Yingchao Piao, Changhua Pei et al.
發表日期：2026-02-02
arXiv：2602.02090
PDF：https://arxiv.org/pdf/2602.02090v2

Constructing domain-specific knowledge graphs from unstructured text remains challenging due to heterogeneous entity mentions, long-tail relation distributions, and the absence of standardized schemas. We present LEC-KG, a bidirectional collaborative framework that integrates the semantic understanding of Large Language Models (LLMs) with the structural reasoning of Knowledge Graph Embeddings (KGE). Our approach features three key components: (1) hierarchical coarse-to-fine relation extraction t...

75. ChronoMedKG: A Temporally-Grounded Biomedical Knowledge Graph and Benchmark for Clinical Reasoning¶

相似度：0.6875
作者：Md Shamim Ahmed, Farzaneh Firoozbakht, Lukas Galke Poech et al.
發表日期：2026-05-21
arXiv：2605.22734
PDF：https://arxiv.org/pdf/2605.22734v1

Biomedical knowledge graphs (KGs) treat disease associations as static facts, but temporal information is crucial for clinical reasoning, e.g., a symptom diagnostic of one disease at age 3 may imply a different disease at age 13. Existing KGs such as PrimeKG, Hetionet, and iKraph do not encode when a finding becomes clinically relevant over the course of a disease. This limits their usefulness for longitudinal clinical reasoning and retrieval augmentation. We introduce ChronoMedKG, a temporal ...

76. UniD$^3$: A Knowledge Graph-Enhanced RAG Framework for Drug-Disease Discovery and Reasoning¶

相似度：0.6874
作者：Qing Wang, Tianshi Liu, Minghao Zhou et al.
發表日期：2026-05-31
arXiv：2606.01394
PDF：https://arxiv.org/pdf/2606.01394v1

Systematic characterization of drug-disease relationships is essential for drug discovery and repurposing, yet is hindered by the heterogeneity and rapid growth of biomedical literature. Existing datasets rely on labor-intensive curation and are often incomplete, while LLM-only approaches suffer from hallucination and weak evidence grounding. We introduce UniD$^3$, a unified framework that integrates Large Language Models with Knowledge Graph-enhanced Retrieval-Augmented Generation (KG-RAG) to e...

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

相似度：0.6871
作者：Jiarui Zhong, Hong Cai Chen
發表日期：2026-05-07
arXiv：2605.05643
PDF：https://arxiv.org/pdf/2605.05643v1

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 "...

78. PrimeKG-CL: A Continual Graph Learning Benchmark on Evolving Biomedical Knowledge Graphs¶

相似度：0.6863
作者：Yousef A. Radwan, Yao Li, Qing Qing et al.
發表日期：2026-05-11
arXiv：2605.10529
PDF：https://arxiv.org/pdf/2605.10529v1

Biomedical knowledge graphs underwrite drug repurposing and clinical decision support, yet the upstream ontologies they depend on update on independent cycles that add millions of edges and deprecate hundreds of thousands more between releases. Yet existing continual graph learning has been studied almost exclusively on synthetic random splits of static, generic KGs, a regime that cannot reproduce the asynchronous, structured evolution real biomedical KGs undergo. To this end, we introduce Prime...

79. ActiShade: Activating Overshadowed Knowledge to Guide Multi-Hop Reasoning in Large Language Models¶

相似度：0.6857
作者：Huipeng Ma, Luan Zhang, Dandan Song et al.
發表日期：2026-01-12
arXiv：2601.07260
PDF：https://arxiv.org/pdf/2601.07260v1

In multi-hop reasoning, multi-round retrieval-augmented generation (RAG) methods typically rely on LLM-generated content as the retrieval query. However, these approaches are inherently vulnerable to knowledge overshadowing - a phenomenon where critical information is overshadowed during generation. As a result, the LLM-generated content may be incomplete or inaccurate, leading to irrelevant retrieval and causing error accumulation during the iteration process. To address this challenge, we prop...

80. GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction¶

相似度：0.6854
作者：Jinze Gu, Qinghua Mao, Xi Lin et al.
發表日期：2026-05-27
arXiv：2605.28645
PDF：https://arxiv.org/pdf/2605.28645v1

Retrieval-Augmented Generation (RAG) enhances LLMs by grounding generation in query-relevant external evidence. Beyond unstructured text corpora, Graph RAG integrates knowledge graphs into the retrieval pipeline, enabling LLMs to access entities, relations, and multi-hop dependencies encoded in structured knowledge. However, the same structured knowledge that empowers Graph RAG also creates a new privacy attack surface. We demonstrate that Graph RAG systems can be turned into structural oracles:...

81. LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling¶

相似度：0.6848
作者：Jiarui Zhao, Rongzhi Zhang, Lingchuan Liu et al.
發表日期：2026-06-11
arXiv：2606.12837
PDF：https://arxiv.org/pdf/2606.12837v2

Search agent benchmarks exemplified by BrowseComp have rapidly saturated over the past year, with the strongest models surpassing 90% accuracy. Since these benchmarks are predominantly human-authored, annotators lack a global perspective on entity statistics and cannot systematically maximize search space size and structural complexity. This creates a difficulty ceiling that is hard to break. To address this, we introduce LoHoSearch (Long-Horizon Search Agents), a challenging benchmark comprisin...

82. CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering¶

相似度：0.6848
作者：Yushi Sun, Lei Chen
發表日期：2026-04-28
arXiv：2604.26176
PDF：https://arxiv.org/pdf/2604.26176v4

The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) has significantly advanced Knowledge Graph Question Answering (KGQA). However, existing LLM-driven KGQA systems act as stateless planners, generating retrieval plans in isolation without exploiting historical query patterns: analogous to a database system that optimizes every query from scratch without a plan cache. This fundamental design flaw leads to schema hallucinations and limited retrieval coverage. ...

83. GraphRAG-IRL: Personalized Recommendation with Graph-Grounded Inverse Reinforcement Learning and LLM Re-ranking¶

相似度：0.6844
作者：Siqi Liang, Xiawei Wang, Yudi Zhang et al.
發表日期：2026-04-21
arXiv：2604.19128
PDF：https://arxiv.org/pdf/2604.19128v1

Personalized recommendation requires models that capture sequential user preferences while remaining robust to sparse feedback and semantic ambiguity. Recent work has explored large language models (LLMs) as recommenders and re-rankers, but pure prompt-based ranking often suffers from poor calibration, sensitivity to candidate ordering, and popularity bias. These limitations make LLMs useful semantic reasoners, but unreliable as standalone ranking engines. We present \textbf{GraphRAG-IRL}, a h...

84. PathISE: Learning Informative Path Supervision for Knowledge Graph Question Answering¶

相似度：0.6843
作者：Shengxiang Gao, Chao Lei, Jey Han Lau et al.
發表日期：2026-05-11
arXiv：2605.10791
PDF：https://arxiv.org/pdf/2605.10791v1

Knowledge Graph Question Answering (KGQA) aims to answer user questions by reasoning over Knowledge Graphs (KGs). Recent KGQA methods mainly follow the retrieval-augmented generation paradigm to ground Large Language Models~(LLMs) with structured knowledge from KGs. However, training effective models to retrieve question-relevant evidence from KGs typically requires high-quality intermediate supervision signals, such as question-relevant paths or subgraphs, which are time- and resource-intensive...

85. HOME-KGQA: A Benchmark Dataset for Multimodal Knowledge Graph Question Answering on Household Daily Activities¶

相似度：0.6841
作者：Shusaku Egami, Aoi Ohta, Tomoki Tsujimura et al.
發表日期：2026-05-10
arXiv：2605.09348
PDF：https://arxiv.org/pdf/2605.09348v1

Large Language Models (LLMs) provide flexible natural language processing capabilities, while knowledge graphs (KGs) offer explicit and structured knowledge. Integrating these two in a complementary manner enables the development of reliable and verifiable AI systems. In particular, knowledge graph question answering (KGQA) has attracted attention as a means to reduce LLM hallucinations and to leverage knowledge beyond the training data. However, existing KGQA benchmark datasets are biased towar...

86. Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval¶

相似度：0.6841
作者：Hamed Jelodar, Samita Bai, Mohammad Meymani et al.
發表日期：2026-04-17
arXiv：2604.15951
PDF：https://arxiv.org/pdf/2604.15951v2

Generative AI, particularly Large Language Models, increasingly integrates graph-based representations to enhance reasoning, retrieval, and structured decision-making. Despite rapid advances, there remains limited clarity regarding when, why, where, and what types of graph-LLM integrations are most appropriate across applications. This survey provides a concise, structured overview of the design choices underlying the integration of graphs with LLMs. We categorize existing methods based on their...

87. FastInsight: Fast and Insightful Retrieval via Fusion Operators for Graph RAG¶

相似度：0.6839
作者：Seonho An, Chaejeong Hyun, Min-Soo Kim
發表日期：2026-01-26
arXiv：2601.18579
PDF：https://arxiv.org/pdf/2601.18579v1

Existing Graph RAG methods aiming for insightful retrieval on corpus graphs typically rely on time-intensive processes that interleave Large Language Model (LLM) reasoning. To enable time-efficient insightful retrieval, we propose FastInsight. We first introduce a graph retrieval taxonomy that categorizes existing methods into three fundamental operations: vector search, graph search, and model-based search. Through this taxonomy, we identify two critical limitations in current approaches: the t...

88. GRASP: Graph Agentic Search over Propositions for Multi-hop Question Answering¶

相似度：0.6837
作者：Stockton Jenkins, Ramya Korlakai Vinayak, Junjie Hu
發表日期：2026-05-15
arXiv：2605.16598
PDF：https://arxiv.org/pdf/2605.16598v1

Agentic retrieval improves multi-hop question answering by giving language models autonomy to iteratively gather evidence. Recent work augments these systems with knowledge graphs for structured traversal, but this combination introduces significant cost: expensive graph construction at index time and compounding token usage at inference time. We introduce Graph Agentic Search over Propositions (GRASP), an agentic system that simultaneously optimizes for high accuracy and minimal token usage in ...

89. PrivGemo: Privacy-Preserving Dual-Tower Graph Retrieval for Empowering LLM Reasoning with Memory Augmentation¶

相似度：0.6829
作者：Xingyu Tan, Xiaoyang Wang, Qing Liu et al.
發表日期：2026-01-13
arXiv：2601.08739
PDF：https://arxiv.org/pdf/2601.08739v1

Knowledge graphs (KGs) provide structured evidence that can ground large language model (LLM) reasoning for knowledge-intensive question answering. However, many practical KGs are private, and sending retrieved triples or exploration traces to closed-source LLM APIs introduces leakage risk. Existing privacy treatments focus on masking entity names, but they still face four limitations: structural leakage under semantic masking, uncontrollable remote interaction, fragile multi-hop and multi-entit...

90. ReGraM: Region-First Knowledge Graph Reasoning for Medical Question Answering¶

相似度：0.6826
作者：Chaerin Lee, Sohee Park, Hyunsik Na et al.
發表日期：2026-01-14
arXiv：2601.09280
PDF：https://arxiv.org/pdf/2601.09280v1

Recent studies in medical question answering (Medical QA) have actively explored the integration of large language models (LLMs) with biomedical knowledge graphs (KGs) to improve factual accuracy. However, most existing approaches still rely on traversing the entire KG or performing large-scale retrieval, which introduces substantial noise and leads to unstable multi-hop reasoning. We argue that the core challenge lies not in expanding access to knowledge, but in identifying and reasoning over t...

91. MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models¶

相似度：0.6820
作者：Weixin Liu, Congning Ni, Shelagh A. Mulvaney et al.
發表日期：2026-05-15
arXiv：2605.15589
PDF：https://arxiv.org/pdf/2605.15589v1

Large language models (LLMs) are increasingly used in the mental health domain, yet it remains unclear how well they capture related biomedical knowledge and how reliably they apply it to clinically salient structured judgments. Here, we present a knowledge-graph (KG)-grounded benchmark for assessing LLMs on mental-health entity recognition, relation judgment, and two-hop reasoning. The benchmark is derived from PrimeKG and comprises nine task families with KG-supported answers and controlled ne...

92. Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation¶

相似度：0.6820
作者：Kwun Hang Lau, Fangyuan Zhang, Boyu Ruan et al.
發表日期：2026-02-02
arXiv：2602.01965
PDF：https://arxiv.org/pdf/2602.01965v1

Recent advances in Retrieval-Augmented Generation (RAG) have shifted from simple vector similarity to structure-aware approaches like HippoRAG, which leverage Knowledge Graphs (KGs) and Personalized PageRank (PPR) to capture multi-hop dependencies. However, these methods suffer from a "Static Graph Fallacy": they rely on fixed transition probabilities determined during indexing. This rigidity ignores the query-dependent nature of edge relevance, causing semantic drift where random walks are dive...

93. LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning¶

相似度：0.6813
作者：Zerui Chen, Qinggang Zhang, Zhishang Xiang et al.
發表日期：2026-05-27
arXiv：2605.28120
PDF：https://arxiv.org/pdf/2605.28120v1

Graph-based Retrieval-Augmented Generation (GraphRAG) advances flat document retrieval by structuring knowledge as relational graphs, enabling more coherent and effective reasoning. However, applying it to specific domains like legal reasoning faces critical challenges. (i) Legal corpora are heterogeneous, containing multi-granular knowledge from cases, articles and interpretations. A flat knowledge graph cannot adequately differentiate between factual details, applied rules, and abstract princi...

94. RAGA: Reading-And-Graph-building-Agent for Autonomous Knowledge Graph Construction and Retrieval-Augmented Generation¶

相似度：0.6812
作者：Chengrui Han, Zesheng Cheng
發表日期：2026-05-16
arXiv：2605.17072
PDF：https://arxiv.org/pdf/2605.17072v1

Existing LLM-driven knowledge graph (KG) construction methods predominantly employ stateless batch processing pipelines, exhibiting structural deficiencies in cross-chunk semantic relation capture, entity disambiguation, and construction process interpretability. These limitations undermine KG quality, retrieval precision, and deployment trust in high-stakes domains. We propose RAGA (Reading And Graph-building Agent), an LLM-based autonomous KG construction and retrieval fusion framework. RAGA...

95. Reliable Graph-RAG for Codebases: AST-Derived Graphs vs LLM-Extracted Knowledge Graphs¶

相似度：0.6811
作者：Manideep Reddy Chinthareddy
發表日期：2026-01-13
arXiv：2601.08773
PDF：https://arxiv.org/pdf/2601.08773v1

Retrieval-Augmented Generation for software engineering often relies on vector similarity search, which captures topical similarity but can fail on multi-hop architectural reasoning such as controller to service to repository chains, interface-driven wiring, and inheritance. This paper benchmarks three retrieval pipelines on Java codebases (Shopizer, with additional runs on ThingsBoard and OpenMRS Core): (A) vector-only No-Graph RAG, (B) an LLM-generated knowledge graph RAG (LLM-KB), and (C) a d...

96. HugRAG: Hierarchical Causal Knowledge Graph Design for RAG¶

相似度：0.6810
作者：Nengbo Wang, Tuo Liang, Vikash Singh et al.
發表日期：2026-02-04
arXiv：2602.05143
PDF：https://arxiv.org/pdf/2602.05143v1

Retrieval augmented generation (RAG) has enhanced large language models by enabling access to external knowledge, with graph-based RAG emerging as a powerful paradigm for structured retrieval and reasoning. However, existing graph-based methods often over-rely on surface-level node matching and lack explicit causal modeling, leading to unfaithful or spurious answers. Prior attempts to incorporate causality are typically limited to local or single-document contexts and also suffer from informatio...

97. GATHER: Convergence-Centric Hyper-Entity Retrieval for Zero-Shot Cell-Type Annotation¶

相似度：0.6810
作者：Zhonghui Zhang, Feng Jiang, Shaowei Qin et al.
發表日期：2026-05-07
arXiv：2605.06403
PDF：https://arxiv.org/pdf/2605.06403v1

Zero-shot single-cell cell-type annotation aims to determine a cell's type from a given set of expressed genes without any training. Existing knowledge-graph-based RAG approaches retrieve evidence by expanding from source entities and relying on iterative LLM reasoning. However, in this setting each query contains tens to hundreds of genes, where no single gene is decisive and the label emerges only from their collective co-occurrence. Such hyper-entity queries fundamentally challenge local, ent...

98. UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough¶

相似度：0.6808
作者：Ryszard Tuora, Mateusz Galiński, Michał Godziszewski et al.
發表日期：2026-02-06
arXiv：2603.29875
PDF：https://arxiv.org/pdf/2603.29875v3

One of the key problems in Retrieval-augmented generation (RAG) systems is that chunk-based retrieval pipelines represent the source chunks as atomic objects, mixing the information contained within such a chunk into a single vector. These vector representations are then fundamentally treated as isolated, independent and self-sufficient, with no attempt to represent possible relations between them. Such an approach has no dedicated mechanisms for handling multi-hop questions. Graph-based RAG sys...

99. SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory¶

相似度：0.6808
作者：Juntong Wang, Haoyue Zhao, guanghui Pan et al.
發表日期：2026-05-12
arXiv：2605.12061
PDF：https://arxiv.org/pdf/2605.12061v1

Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits their ability to recover complete evidence chains from partial cues, exploit reusable graph-structrual roles, and improve the memory itself through downstream feedback. We introduce SAGE, a Self-evolving Agentic Graph-memory Engine that models graph memory as a dynamic long-term memory substrate. SAGE couples two roles: a...

100. SkillGraph: Graph Foundation Priors for LLM Agent Tool Sequence Recommendation¶

相似度：0.6806
作者：Hao Liu, Dongyu Li
發表日期：2026-04-07
arXiv：2604.19793
PDF：https://arxiv.org/pdf/2604.19793v1

LLM agents must select tools from large API libraries and order them correctly. Existing methods use semantic similarity for both retrieval and ordering, but ordering depends on inter-tool data dependencies that are absent from tool descriptions. As a result, semantic-only methods can produce negative Kendall-$τ$ in structured workflow domains. We introduce SkillGraph, a directed weighted execution-transition graph mined from 49,831 successful LLM agent trajectories, which encodes workflow-prece...