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 AgenticT2S, 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 AgenticT2S improves execution accuracy by 17.3% and triple level F1 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.
@article{arxiv.2508.01815,
title = {AGENTICT$^2$S:Robust Text-to-SPARQL via Agentic Collaborative Reasoning over Heterogeneous Knowledge Graphs for the Circular Economy},
author = {Yang Zhao and Chengxiao Dai and Wei Zhuo and Tan Chuan Fu and Yue Xiu and Dusit Niyato and Jonathan Z. Low and Eugene Ho Hong Zhuang and Daren Zong Loong Tan},
journal= {arXiv preprint arXiv:2508.01815},
year = {2025}
}