1
Towards a Universal Causal Reasoner
提出UniCo数据集和训练范式，让LLM成为通用因果推理器，突破现有基准局限。
arXiv:2605.24873v1 Announce Type: cross Abstract: Despite the importance of causal reasoning, training LLMs to reason causally remains underexplored. …
2
Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
为冻结的大语言模型打造即插即用通用推理器，无需微调即可增强模型推理能力
arXiv:2505.19075v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable general capabilities, but enhancin…
3
Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems
用超图本体打破LLM在企业系统中的幻觉与审计困境，HEAR在供应链根因分析上实现94.7%准确率，为多跳、n元推理提供了无需重训的可扩展范式。
arXiv:2605.14259v1 Announce Type: new Abstract: Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucination…