TCR-Former：用因果拓扑注意力让 8.6B 模型时序因果推理超越 GPT-5.4
From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning
一篇时序因果推理的论文，8.6B 参数的 TCR-Former 在 TempoCausal 上赢了 GPT-5.4 和 DeepSeek-V3.2，思路是把因果图塞进注意力机制里。
论文提出从离散叙事转向因果拓扑的时序因果推理范式，构建了免训练的 TCR-Agent 和端到端的 TCR-Former 两种架构。TCR-Agent 通过外部因果图实例化和符号干预引擎实现可解释的因果推演与反事实截断。TCR-Former 用 Causal-Topological Attention Mask 把这些机制内化到 Transformer 注意力空间，在 TempoCausal 基准上比 SOTA 方法准确率高出 16.5%，仅以约 8.6B 参数超过 GPT-5.4 和 DeepSeek-V3.2。分析还发现现有方法存在结构-推理脱节现象：符号约束和思维链只能增加推理步骤，无法提升深层因果演绎能力。
From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning
Large language models (LLMs) generally lack deep causal reasoning capabilities in temporal reasoning. Inspired by document layout reordering, this paper proposes a paradigm shift from discrete narratives to causal topologies. It constructs two architectures: a training-free neuro-symbolic framework, temporal causal reasoning agent (TCR-Agent), which achieves interpretable causal deduction and counterfactual truncation through external causal graph instantiation and a symbolic intervention engine; and an end-to-end model, temporal causal reasoning former (TCR-Former), which internalizes these mechanisms into the Transformer attention space via a Causal-Topological Attention Mask and temporal span biases. Experiments on the TempoCausal benchmark demonstrate that TCR-Agent comprehensively surpasses existing training-free baselines. At the same time, TCR-Former achieves an accuracy 16.5% higher than that of state-of-the-art (SOTA) methods, outperforming large-scale models such as GPT-5.4 and DeepSeek-V3.2 with only approximately 8.6B parameters. Further analysis reveals a structure-reasoning disconnection phenomenon in existing methods: external symbolic constraints and chain-of-thought reasoning can improve reasoning steps, yet fail to enhance deep causal deductive capability. By internalizing temporal causal reasoning capabilities into the model, TCR-Former effectively bridges this gap, providing an efficient and reliable end-to-end foundation for complex reasoning scenarios.