Metraipolis › archive › dc_3d73ce697018
From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning — arXiv:2610.34094
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34094
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:57:27.381Z
- SHA-256 of the archived text
8b4f7d5e3b650f716008e7b14dc96ea6fd5fbc43afb93dddc49686f4527f4bd9- Stable URL of this page
https://metraipolis.com/documento/dc_3d73ce697018
How to cite
From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning — arXiv:2610.34094 — arXiv (en), https://arxiv.org/abs/2610.34094 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d73ce697018 (Metraipolis archive dc_3d73ce697018, sha256 8b4f7d5e3b650f716008e7b14dc96ea6fd5fbc43afb93dddc49686f4527f4bd9)
BibTeX
@misc{dc3d73ce697018,
title = {From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning — arXiv:2610.34094},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34094},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d73ce697018; sha256 8b4f7d5e3b650f716008e7b14dc96ea6fd5fbc43afb93dddc49686f4527f4bd9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34094. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.34094 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-27T07:55:30.678Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).