揭秘图序列化对LLM推理泛化性的关键影响，挑战现有图推理范式。
arXiv:2511.10234v3 Announce Type: replace-cross Abstract: While promising, graph reasoners based on Large Language Models (LLMs) lack built-in invaria…
新的上下文图推理范式，无需参数更新即可在图中实现快速预测与结构归纳。
arXiv:2606.05042v1 Announce Type: cross Abstract: Marginal inference in discrete graphical models forces a choice between exactness and scalability: e…
两阶段课程后训练让LLM学会在图数据中探索和推理，创新训练方法带来更强推理能力。
arXiv:2602.02518v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly rely on external knowledge to improve factuality, …