用符号规则约束大模型，让世界模型更准且省数据。
Neuro-Symbolic Synergy for Interactive World Modeling
- 大模型+符号规则交替训练，互相修正不足。
- 在三个交互环境上准确率更高，数据量少一半仍有效。
- 适合需要可靠推理的智能体开发与强化学习应用。
大型语言模型（LLM）具备强大的通用推理能力，但在作为世界模型（WM）时容易产生幻觉，而符号世界模型虽逻辑严谨却缺乏语义表达力。为此，我们提出神经符号协同框架NeSyS，将LLM的概率语义先验与可执行的符号规则结合，兼顾表达力与鲁棒性。该框架通过轨迹交替训练两个模型：符号模型直接修改LLM输出的概率分布以施加约束；神经模型仅在符号规则未覆盖的轨迹上微调，使训练数据减少50%而不损失精度。在ScienceWorld、Webshop和Plancraft三个交互环境中，实验表明NeSyS在世界模型预测准确率和数据效率上均优于基线。代码与模型已开源。
原文摘要 · Abstract (English)
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. Our models and code are available at https://github.com/tianyi-lab/NeSyS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。