Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.11770 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908654434779136 |
|---|---|
| author | Vossebeld, Floris Wang, Shenghui |
| author_facet | Vossebeld, Floris Wang, Shenghui |
| contents | Generating complex, logically-sound SPARQL queries for multi-hop questions remains a critical bottleneck for Knowledge Graph Question Answering, as the brittle nature of one-shot generation by Large Language Models (LLMs) hinders reliable interaction with structured data. Current methods lack the adaptive policies needed to dynamically debug queries based on real-time execution feedback. This paper introduces a novel agentic framework where an LLM learns a resilient policy for the sequential process of iterative SPARQL construction. We show that a compact 3B-parameter model, trained exclusively via outcome-driven Reinforcement Learning (GRPO) without supervised fine-tuning, can learn effective policies for this task, discovering how to systematically recover from execution errors and refine its queries toward a correct answer. On a curated, executable single-answer subset of LC-QuAD 2.0, our agent achieves 49.7\% accuracy post-entity-linking, a significant 17.5 percentage point improvement over the strongest iterative zero-shot baseline. Further analysis reveals that while the agent's capability is driven by RL, its performance is enhanced by an explicit deliberative reasoning step that acts as a cognitive scaffold to improve policy precision. This work presents a generalizable blueprint for teaching agents to master formal, symbolic tools through interaction, bridging the gap between probabilistic LLMs and the structured world of Knowledge Graphs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11770 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction Vossebeld, Floris Wang, Shenghui Artificial Intelligence Machine Learning 68P20, 68T42 H.3.3; I.2.4 Generating complex, logically-sound SPARQL queries for multi-hop questions remains a critical bottleneck for Knowledge Graph Question Answering, as the brittle nature of one-shot generation by Large Language Models (LLMs) hinders reliable interaction with structured data. Current methods lack the adaptive policies needed to dynamically debug queries based on real-time execution feedback. This paper introduces a novel agentic framework where an LLM learns a resilient policy for the sequential process of iterative SPARQL construction. We show that a compact 3B-parameter model, trained exclusively via outcome-driven Reinforcement Learning (GRPO) without supervised fine-tuning, can learn effective policies for this task, discovering how to systematically recover from execution errors and refine its queries toward a correct answer. On a curated, executable single-answer subset of LC-QuAD 2.0, our agent achieves 49.7\% accuracy post-entity-linking, a significant 17.5 percentage point improvement over the strongest iterative zero-shot baseline. Further analysis reveals that while the agent's capability is driven by RL, its performance is enhanced by an explicit deliberative reasoning step that acts as a cognitive scaffold to improve policy precision. This work presents a generalizable blueprint for teaching agents to master formal, symbolic tools through interaction, bridging the gap between probabilistic LLMs and the structured world of Knowledge Graphs. |
| title | Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction |
| topic | Artificial Intelligence Machine Learning 68P20, 68T42 H.3.3; I.2.4 |
| url | https://arxiv.org/abs/2511.11770 |