Progressive Planning and Reinforced Reasoning: Large Language Model-Guided Multi-hop Question Answering over Knowledge Graph

Reinforcement learning, with its interpretable path reasoning, has emerged as a promising paradigm for multi-hop question answering over knowledge graphs. However, existing approaches suffer from two inherent limitations: (1) lacking effective intermediate guidance, agents often fall into aimless exploration when confronted with complex multi-hop questions; and (2) policy networks focus on local neighborhood information, making it difficult to anticipate the long-term consequences of decisions. To address these challenges, we propose a Progressive Planning and Reinforced Reasoning (PPRR) framework. Specifically, we introduce large language models as multihop reasoning planners, converting decomposed sub-question sequences into stepwise decision guidance and thereby granting the agent human-like, step-by-step problem-solving capabilities. In addition, we design a structureaware lookahead policy network, which explicitly models inter-node dependencies along the multi-hop reasoning process and performs lookahead value evaluations for candidate actions, thereby enhancing the agent's global state awareness and decision foresight in complex environments. Finally, we conducted extensive experiments on four public multi-hop question answering benchmarks and one domainspecific dataset. The results demonstrate that our framework surpasses state-of-the-art methods while demonstrating strong generalization.