LLM能像人类一样构造特殊图吗？这个数据集专门来测，为图论+AI交叉研究提供新基准。
arXiv:2608.14999v1 Announce Type: cross Abstract: Constructing special graphs is an important task within graph theory and computer science. Many popu…
AI模型GPT-5.6 Sol Ultra首次给出图论Cycle Double Cover猜想的完整证明，数学界迎来机器推理里程碑。
https://x.com/__eknight__/status/2075643450196971805 , https://xcancel.com/__eknight__/status/2075643450196971805 Prompt: https://cdn.openai.com/pdf/0…
用图论框架量化大模型逻辑推理的可信度，为评估LLM可靠性提供新方法。
arXiv:2607.08017v1 Announce Type: new Abstract: Large-Language Models (LLMs) can be prone to flawed and unfaithful reasoning that decoding strategies …
首个课程化评估基准，专测大模型在图论领域作为数学研究助手的推理能力
arXiv:2606.03144v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as self-study assistants in technical disciplines, …
用图曲率衡量连接重要性，提供神经网络剪枝新视角，高效保留关键数据流。
arXiv:2601.16366v2 Announce Type: replace Abstract: This paper provides a fresh view of the neural network (NN) pruning problem through the lens of gr…
用图论方法构建更可靠的LLM评审，专门用于评估检索系统质量，无需人工标注ground truth。
Article URL: https://georgianailab.substack.com/p/evaluating-retrieval-without-ground Comments URL: https://news.ycombinator.com/item?id=48323562 Poin…
图上的Matérn高斯过程：理论推导与图结构结合的创新方法，为图数据建模提供新视角。
arXiv:2010.15538v4 Announce Type: replace-cross Abstract: Gaussian processes are a versatile framework for learning unknown functions in a manner that…