This work presents an agentic text-to-SPARQL system that goes one step beyond static tool-using agents: a researcher agent that, after each round of inference on a validation set, proposes and tests changes to its own prompts, rules, and tool-orchestration code.
Abstract
Translating a natural-language question into a SPARQL query that can be executed against a large knowledge graph requires resolving lexical ambiguity, grounding surface terms in the target ontology, and producing graph patterns that are both syntactically valid and semantically faithful. We present an agentic text-to-SPARQL system that goes one step beyond static tool-using agents: a researcher agent that, after each round of inference on a validation set, proposes and tests changes to its own prompts, rules, and tool-orchestration code. We instantiate the loop on DBpedia, evolve nine successive versions of the agent driven by a low-cost reasoning model, and deploy the best-performing configuration with two stronger backbone models. The study yields three observations: (i) self-improvement converges quickly and then achieves 0.22 overall accuracy on the 2025 DBpedia validation set; (ii) the bottleneck is consistently in basic-graph-pattern predicate selection, not in SPARQL syntax or modifiers; and (iii) several benchmark items appear to penalise correct queries due to property ambiguity in DBpedia, suggesting that future Text-to-SPARQL benchmarks should be scored using a combination of machine translation and information retrieval metrics.
Complex knowledge base question answering (KBQA) is commonly approached through either information retrieval over a question-specific subgraph or semantic parsing into an executable logical form. We study the latter paradigm. Recent large language model agents make semantic parsing interactive: they alternate between reasoning, querying the knowledge base, and extending a partial SPARQL query. This interleaving reduces reliance on one-shot generation, but makes the quality of \emph{KB grounding} depend on what the interaction tools expose. Existing agents retrieve or prune candidate properties mainly through lexical relevance and instance-level observations, without systematically conditioning on entity types, property domains and ranges, or the expected answer type. We call this failure mode \emph{type-blind grounding}. It enlarges the grounding search space and often produces plausible-looking but semantically incompatible triple patterns that execute to empty results. We propose SAGA (\underline{S}chema-\underline{A}ware \underline{G}rounding for \underline{A}gentic Text-to-SPARQL Generation), a training-free framework that turns property exploration into a schema-constrained grounding operation. SAGA maintains a persistent bidirectional type state, filters known-incompatible property candidates at construction time, presents the remaining graph patterns in a compact schema-annotated format, and handles missing schema information permissively through empirical and trace-local evidence. Across nine benchmark settings over Wikidata and Freebase, SAGA achieves the highest F1 on all nine settings and the highest exact-match accuracy on eight, while reducing empty-result queries across all reported Wikidata settings.
This paper studies the VKG-QA task, which enables users to interact with the VKGs through a natural language (NL) interface by translating their questions into SPARQL queries, and pro-poses NaVQA (Navigation-based VKG Question Answering), a framework leveraging Large Language Models.
Guohui Xiao, Haohan Xue, Lin Ren et al.· 0 citations
Knowledge Graph Question Answering (KGQA) over RDF graphs remains challenging in domain-specific settings, where formal ontologies and curated text-SPARQL pairs are often unavailable. We present KGVoyager, a KG-agnostic agentic architecture that generates SPARQL queries from natural language questions by dynamically discovering graph structure and semantics, requiring only a query endpoint of the underlying graph. Using a think-act-observe loop with search, exploration, and execution tools, KGVoyager maps terms to graph IRIs, uncovers structure, and refines queries through execution feedback - all without pre-existing ontologies or examples. Unlike the prior state of the art, KGVoyager requires only a lightweight class index which renders it applicable for far more real-world endpoints. Across four benchmarks, KGVoyager improves F1 by ~8 points while cutting cost and runtime by ~22% each.
SEGRA is introduced, an experience-guided agent for enterprise text-to-Gremlin question answering that integrates intent routing, schema- and taxonomy-grounded query generation, multi-shot decomposition, execution-aware verification, and a curriculum-bootstrapped skill library that reuses verified query patterns.
Saiyue Lyu, Mariam Dundua, Vishaal Kapoor et al.· 0 citations
We present EXYGEN (EXplore Your Graphs ENgine), a framework for knowledge graph (KG) understanding that enables conversational access to KGs at scale. We address two questions in sequence. First, how effectively can LLMs perform text-to-SPARQL generation given only automatically derived structured metadata and small graph samples, rather than task-specific fine-tuning? We integrate VoID descriptions and ShEx schemas into a retrieval-augmented generation (RAG) pipeline and ablate KG-derived context on the SciQA benchmark. Our best configuration -- combining ShEx schemas, retrieved triples, and example question-query pairs -- reaches an exact match of 0.419 on execution results without any LLM fine-tuning. We further find that lexical metrics such as F1 poorly predict query correctness, and that larger general-purpose LLMs can outperform smaller code-specialized ones once given sufficient context. Second, we ask how to generate the structured metadata that this method relies on from very large KGs, where KG metadata generation becomes computationally intractable. We introduce a predicate-coverage-aware parallel graph sampling strategy that preserves structural diversity while remaining computationally tractable. On OpenCitations Meta and GESIS, it retains high predicate coverage with minimal triple loss and reduces runtime by over 80x; on ORKG, sampling is not just faster but the only tractable path to obtain complete metadata. Together, these results show that structured schema context and lightweight prompting can substantially reduce reliance on fine-tuning for scalable conversational access to KGs, though closing the remaining gap to fully fine-tuned approaches will likely require reducing dependence on curated question-query exemplars -- whether through synthetic generation or an execution-feedback-driven approach -- and validating these findings beyond a single benchmark.
Harshdeep Singh, Yu-Rui Zhu, Giovanni Colavizza et al.· 0 citations
In order to enable natural language interaction with structured knowledge bases based on ontologies, widely used to represent knowledge in multiple complex domains, Knowledge Graph Question Answering (KGQA) systems are required. Large Language Models (LLMs) can play a pivotal role in this context, however they suffer from factual inaccuracies, hallucinations, and difficulties in navigating complex semantic schemas. To address these limitations, this paper proposes a novel neuro-symbolic Agentic AI framework for KGQA on real-world knowledge graph. By integrating neural reasoning capabilities of LLMs with symbolic tools within a recursive flow orchestrated by LangGraph, the system is able to identify relevant terms, validate them based on specific ontology, and generate SPARQL queries for data retrieval. To demonstrate effectiveness of this approach an experimental evaluation using a real-world smart city knowledge base, implemented in the Snap4City platform, is carried out. Results indicate that the neuro-symbolic workflows improves the accuracy of information retrieval for non-expert users compared to standalone LLM solutions.
Zahra Fereidooni, M. Fanfani, G. Pantaleo et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
