# Towards Researcher Agents for Knowledge-Graph Question Answering

arXiv: https://arxiv.org/abs/2608.07700 · HTML: https://mlsanity.com/paper/2608.07700/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Builds on (most cited first, 15 of 15)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base](https://mlsanity.com/paper/2007.03875/) (2020)
- [SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases](https://mlsanity.com/paper/2003.13956/) (2020)
- [QALD-9-plus: A Multilingual Dataset for Question Answering over DBpedia and Wikidata Translated by Native Speakers](https://mlsanity.com/paper/2202.00120/) (2022)
- [Modern Baselines for SPARQL Semantic Parsing](https://mlsanity.com/paper/2204.12793/) (2022)
- [A Universal Question-Answering Platform for Knowledge Graphs](https://mlsanity.com/paper/2303.00595/) (2023)
- [SPARQL as a Foreign Language](https://mlsanity.com/paper/1708.07624/) (2017)
- [Neural Machine Translation for Query Construction and Composition](https://mlsanity.com/paper/1806.10478/) (2018)
- [A Survey on Neural Question Generation: Methods, Applications, and Prospects](https://mlsanity.com/paper/2402.18267/) (2024)
- [SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decoding](https://mlsanity.com/paper/2407.01626/) (2024)
- [Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answering](https://mlsanity.com/paper/2502.03992/) (2025)
- [ARUQULA -- An LLM based Text2SPARQL Approach using ReAct and Knowledge Graph Exploration Utilities](https://mlsanity.com/paper/2510.02200/) (2025)
- [Integrating Multi-Head Convolutional Encoders with Cross-Attention for Improved SPARQL Query Translation](https://mlsanity.com/paper/2408.13432/) (2024)
- [Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training](https://mlsanity.com/paper/2410.05731/) (2024)

## Abstract (arXiv)

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.