让大模型通过实地思考，结合真实世界信息推理。
SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking
- 用强化学习驱动模型主动获取外部信息，动态融合内部知识
- 在多跳问答和数学推理上显著提升性能，超越原有知识边界
- 能泛化到知识库查询、表格问答等新任务，适合需要现实交互的场景
大语言模型虽具备强大推理能力，但受限于内部参数空间，难以获取实时信息或理解物理世界。为此，我们提出SituatedThinker框架，通过情境化思维使模型在真实世界背景下进行推理，自适应地结合内部知识与外部信息，并通过预定义接口实现交互。利用强化学习机制，鼓励模型主动获取外部信息与反馈，突破知识局限，增强推理能力。实验表明，该方法在多跳问答与数学推理基准上表现显著提升；同时，在未见过的任务如知识库问答（KBQA）、表格问答（TableQA）及文本游戏等场景中也展现出良好的泛化能力，验证了其通用的真实世界接地推理能力。代码已公开于https://github.com/jnanliu/SituatedThinker。
原文摘要 · Abstract (English)
Recent advances in large language models (LLMs) demonstrate their impressive reasoning capabilities. However, the reasoning confined to internal parametric space limits LLMs' access to real-time information and understanding of the physical world. To overcome this constraint, we introduce SituatedThinker, a novel framework that enables LLMs to ground their reasoning in real-world contexts through situated thinking, which adaptively combines both internal knowledge and external information with predefined interfaces. By utilizing reinforcement learning, SituatedThinker incentivizes deliberate reasoning with the real world to acquire information and feedback, allowing LLMs to surpass their knowledge boundaries and enhance reasoning. Experimental results demonstrate significant performance improvements on multi-hop question-answering and mathematical reasoning benchmarks. Furthermore, SituatedThinker demonstrates strong performance on unseen tasks, such as KBQA, TableQA, and text-based games, showcasing the generalizable real-world grounded reasoning capability. Our codes are available at https://github.com/jnanliu/SituatedThinker.
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。