AGENTICT$^2$S:Robust Text-to-SPARQL via Agentic Collaborative Reasoning over Heterogeneous Knowledge Graphs for the Circular Economy

TL;DR

This paper introduces AgenticT$^2$S, a modular agent-based framework for robust text-to-SPARQL question answering over heterogeneous knowledge graphs, especially in low-resource and multi-graph domains like the circular economy.

Contribution

It proposes a novel agentic, modular approach with subtask decomposition, weak-to-strong alignment, and validation strategies to improve KGQA accuracy and scalability across multiple graphs.

Findings

Improves execution accuracy by 17.3% over baselines.

Increases triple level F1 by 25.4%.

Reduces average prompt length by 46.4%.

Abstract

Question answering over heterogeneous knowledge graphs (KGQA) involves reasoning across diverse schemas, incomplete alignments, and distributed data sources. Existing text-to-SPARQL approaches rely on large-scale domain-specific fine-tuning or operate within single-graph settings, limiting their generalizability in low-resource domains and their ability to handle queries spanning multiple graphs. These challenges are particularly relevant in domains such as the circular economy, where information about classifications, processes, and emissions is distributed across independently curated knowledge graphs (KGs). We present AgenticT$^2$S, a modular framework that decomposes KGQA into subtasks managed by specialized agents responsible for retrieval, query generation, and verification. A scheduler assigns subgoals to different graphs using weak-to-strong alignment strategies. A two-stage verifier detects structurally invalid and semantically underspecified queries through symbolic validation and counterfactual consistency checks. Experiments on real-world circular economy KGs demonstrate that AgenticT$^2$S improves execution accuracy by 17.3% and triple level F$_1$ by 25.4% over the best baseline, while reducing the average prompt length by 46.4%. These results demonstrate the benefits of agent-based schema-aware reasoning for scalable KGQA and support decision-making in sustainability domains through robust cross-graph reasoning.