Large language models (LLMs) exhibit strong general-purpose reasoning capabilities, yet they frequently hallucinate when used as world models (WMs), where strict compliance with deterministic transition rules--particularly in corner cases--is essential. In contrast, Symbolic WMs provide logical consistency but lack semantic expressivity. To bridge this gap, we propose Neuro-Symbolic Synergy (NeSyS), a framework that integrates the probabilistic semantic priors of LLMs with executable symbolic rules to achieve both expressivity and robustness. NeSyS alternates training between the two models using trajectories inadequately explained by the other. Unlike rule-based prompting, the symbolic WM directly constrains the LLM by modifying its output probability distribution. The neural WM is fine-tuned only on trajectories not covered by symbolic rules, reducing training data by 50% without loss of accuracy. Extensive experiments on three distinct interactive environments, i.e., ScienceWorld, Webshop, and Plancraft, demonstrate NeSyS's consistent advantages over baselines in both WM prediction accuracy and data efficiency.

翻译：大型语言模型（LLMs）展现出强大的通用推理能力，但在用作世界模型（WMs）时经常产生幻觉，而世界模型必须严格遵守确定性转移规则——尤其在极端情况下。相比之下，符号世界模型提供了逻辑一致性，但缺乏语义表达能力。为弥补这一差距，我们提出神经符号协同框架（NeSyS），该框架将LLMs的概率语义先验与可执行的符号规则相结合，以实现表达性与鲁棒性的统一。NeSyS通过交替训练两种模型，利用对方未能充分解释的轨迹进行学习。与基于规则的提示方法不同，符号世界模型通过修改LLM的输出概率分布直接约束其行为。神经世界模型仅针对符号规则未覆盖的轨迹进行微调，在保持准确性的同时将训练数据减少50%。在三个不同的交互环境（即ScienceWorld、Webshop和Plancraft）上进行的大量实验表明，NeSyS在世界模型预测准确性和数据效率方面均持续优于基线方法。