2026· Proceedings of the 15th International Conference on Data Science, Technology and Applications· 0 citations· 20 references
TL;DR
A scalable Agentic GraphRAG architecture structured under a comprehensive LLMOps Feature-Extraction-Inference (FTI) lifecycle, which achieves a 70% improvement in Citation Rate compared to standard Vector RAG and establishes a robust Safe Abstention rate, effectively mitigating the risk of ungrounded generation.
Abstract
: The dispersal and interdependence of regulations pose significant challenges for Artificial Intelligence (AI) systems in high-compliance domains, where regulatory adherence requires absolute lexical precision and multi-hop relational reasoning. Traditional vector-based Retrieval-Augmented Generation (RAG) often fails in these scenarios, leading to structural hallucinations and a lack of institutional grounding. This paper proposes a scalable Agentic GraphRAG architecture structured under a comprehensive LLMOps Feature-Extraction-Inference (FTI) lifecycle. The core innovation is a deterministic Hybrid Vector-to-Graph coupling (Chunk-to-Entity Mapping) orchestrated by autonomous agents via the Model Context Protocol (MCP), ensuring strict referential integrity through batch schema synchronization. Experimental results on a normative academic benchmark demonstrate that while standard Vector RAG may offer marginal semantic fluency, the proposed Agentic GraphRAG definitively prioritizes auditability. Specifically, the architecture achieves a 70% improvement in Citation Rate compared to standard Vector RAG and establishes a robust Safe Abstention rate of 0.1800, effectively mitigating the risk of ungrounded generation. Furthermore, a FinOps evaluation across multiple Large Language Models (LLMs) validates the system’s cost-effectiveness, successfully optimizing the compliance-to-cost ratio for sustainable enterprise deployment.
Retrieval-augmented generation (RAG) architectures have become central to large language model (LLM) deployment in regulated domains; however, persistent challenges around trust, auditability, and compliance limit their suitability for high-stakes decision support. Prior studies highlight that opaque retrieval chains, probabilistic reasoning, and weak provenance tracking contribute to trust deficits and hallucination risks in RAG-based systems. To address these limitations, this work proposes a trust-aware agentic hybrid architecture that integrates vector-based retrieval with explicit knowledge graph (KG) reasoning, enabling structured constraint enforcement alongside semantic retrieval. The methodology combines architectural system-level design with comparative analysis against conventional RAG pipelines and conceptual validation across regulated use-case scenarios. By leveraging KGs for deterministic reasoning, provenance anchoring, and policy encoding, the hybrid approach is designed to improve traceability of model outputs, reduce hallucination susceptibility, and enhance compliance reasoning compared to vector-only RAG systems. The analysis suggests that agentic orchestration over hybrid retrieval modalities provides a viable pathway toward trustworthy and auditable AI systems. This work contributes a conceptual and architectural foundation for deploying compliant RAG-based AI in regulated environments such as healthcare, finance, and governance, where accountability and explainability are nonnegotiable requirements.
Sivarama Krishna Akhil Koduri· Annual International Compute...· 0 citations
EvoGraph-R1 is introduced, a self-evolving GraphRAG framework that reconceptualizes knowledge graphs as dynamic environments shaped through agent interactions, establishing self-evolving knowledge graphs as a fundamental paradigm across modalities.
Jiashi Lin, Changhong Jiang, Xiangru Lin et al.· 1 citation
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 et al.· 0 citations
A hybrid knowledge graph generation pipeline that grounds a Large Language Model in the Wikidata multilingual Knowledge Graph while employing an agentic reflexion pattern to synthesize emerging concepts and their associated metadata to generate a comprehensive skills knowledge graph.
Emma Jouffroy, Warren Jouanneau, Marc Palyart· 0 citations
Worldbuilding, the construction of coherent fictional worlds, is a foundational task in game design and literary creation. Large Language Models (LLMs) offer new possibilities for automated content generation, but their application to worldbuilding faces three challenges: context explosion that grows linearly with the building process, the tension between creative diversity and content consistency, and the absence of automated quality assurance. This paper presents AutoWorldBuilder, a multi-agent collaborative system that addresses these challenges through five integrated components: a structured concept network with conflict detection; a DAG-based hybrid batch scheduler that groups tasks by semantic locality; a four-layer context compression mechanism achieving approximately 90% token reduction; an iterative review system with specialized Auditor agents that improves proposal pass rates from 42% to over 85%; and a skill-driven agent architecture supporting zero-code extension with differentiated temperature configuration. Two experiments across 20 diverse worldbuilding tasks, using GPT-OSS 120B and DeepSeek v3.2 as LLM backends, demonstrate a 95.0% success rate. The system generated 56-103 self-consistent concepts per world in 18-31 minutes with zero-conflict delivery. The architectural patterns validated here, including layer-as-budget compression, semantic-locality scheduling, and separation of generation and review, transfer to the broader class of knowledge-intensive, multi-agent LLM applications.
Jingbo Chen, He Wang, Wei Yuan et al.· 0 citations
The Semantic Shapley Value (SSV) is defined to allocate contribution over semantic support logic, and SLIC is introduced, a single-trajectory algorithm that constructs the semantic hypergraph, recovers minimal semantic supports, applies Boolean absorption, and computes SSV without rerunning agent subsets.