A Collaborative Reasoning Framework Powered by Reinforcement Learning and Large Language Models for Complex Questions Answering over Knowledge Graph

Zhiqiang Zhang, Wen Zhao


Abstract
Knowledge Graph Question Answering (KGQA) aims to automatically answer natural language questions by reasoning across multiple triples in knowledge graphs (KGs). Reinforcement learning (RL)-based methods are introduced to enhance model interpretability. Nevertheless, when addressing complex questions requiring long-term reasoning, the RL agent is usually misled by aimless exploration, as it lacks common learning practices with prior knowledge. Recently, large language models (LLMs) have been proven to encode vast amounts of knowledge about the world and possess remarkable reasoning capabilities. However, they often encounter challenges with hallucination issues, failing to address complex questions that demand deep and deliberate reasoning. In this paper, we propose a collaborative reasoning framework (CRF) powered by RL and LLMs to answer complex questions based on the knowledge graph. Our approach leverages the common sense priors contained in LLMs while utilizing RL to provide learning from the environment, resulting in a hierarchical agent that uses LLMs to solve the complex KGQA task. By combining LLMs and the RL policy, the high-level agent accurately identifies constraints encountered during reasoning, while the low-level agent conducts efficient path reasoning by selecting the most promising relations in KG. Extensive experiments conducted on four benchmark datasets clearly demonstrate the effectiveness of the proposed model, which surpasses state-of-the-art approaches.
Anthology ID:
2025.coling-main.712
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10672–10684
Language:
URL:
https://aclanthology.org/2025.coling-main.712/
DOI:
Bibkey:
Cite (ACL):
Zhiqiang Zhang and Wen Zhao. 2025. A Collaborative Reasoning Framework Powered by Reinforcement Learning and Large Language Models for Complex Questions Answering over Knowledge Graph. In Proceedings of the 31st International Conference on Computational Linguistics, pages 10672–10684, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
A Collaborative Reasoning Framework Powered by Reinforcement Learning and Large Language Models for Complex Questions Answering over Knowledge Graph (Zhang & Zhao, COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.712.pdf