@inproceedings{chen-etal-2026-topo,
title = "Topo-Narrator: Heterogeneous Topological Memory for Long-form Narrative Generation",
author = "Chen, Kai and
Zhang, Haoran and
Lan, Tian and
Duo, Zehua and
Li, Jiang and
Gao, Guanglai and
Su, Xiangdong",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-short.59/",
pages = "923--944",
ISBN = "979-8-89176-440-8",
abstract = "Long-form narrative generation requires maintaining multi-dimensional consistency over extensive contexts, covering long-term constraints in character settings, event causality, spatial rules, and worldviews. Existing methods compress these heterogeneous elements into homogeneous representations, creating a topological mismatch that lowers retrieval signal-to-noise ratios and induces long-range logical collapse. We propose Topo-Narrator, a framework built on two complementary decouplings. Heterogeneous Topological Memory (HTM) organizes narrative state into a Character Graph, a Plot Chain, and an Environment Tree, providing topology-specific inductive biases. Plan-Reason-Write (PRW) multi-agent collaboration separates high-level reasoning, memory retrieval, and stylistic realization across dedicated agents. Experiments on MoPS and WritingPrompts show that Topo-Narrator consistently generates coherent narratives averaging over 13,000 words and substantially outperforms strong baselines on HANNA quality and fine-grained consistency metrics, validated by three frontier LLM judges and human evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-topo">
<titleInfo>
<title>Topo-Narrator: Heterogeneous Topological Memory for Long-form Narrative Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zehua</namePart>
<namePart type="family">Duo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanglai</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangdong</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-440-8</identifier>
</relatedItem>
<abstract>Long-form narrative generation requires maintaining multi-dimensional consistency over extensive contexts, covering long-term constraints in character settings, event causality, spatial rules, and worldviews. Existing methods compress these heterogeneous elements into homogeneous representations, creating a topological mismatch that lowers retrieval signal-to-noise ratios and induces long-range logical collapse. We propose Topo-Narrator, a framework built on two complementary decouplings. Heterogeneous Topological Memory (HTM) organizes narrative state into a Character Graph, a Plot Chain, and an Environment Tree, providing topology-specific inductive biases. Plan-Reason-Write (PRW) multi-agent collaboration separates high-level reasoning, memory retrieval, and stylistic realization across dedicated agents. Experiments on MoPS and WritingPrompts show that Topo-Narrator consistently generates coherent narratives averaging over 13,000 words and substantially outperforms strong baselines on HANNA quality and fine-grained consistency metrics, validated by three frontier LLM judges and human evaluation.</abstract>
<identifier type="citekey">chen-etal-2026-topo</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-short.59/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>923</start>
<end>944</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Topo-Narrator: Heterogeneous Topological Memory for Long-form Narrative Generation
%A Chen, Kai
%A Zhang, Haoran
%A Lan, Tian
%A Duo, Zehua
%A Li, Jiang
%A Gao, Guanglai
%A Su, Xiangdong
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-440-8
%F chen-etal-2026-topo
%X Long-form narrative generation requires maintaining multi-dimensional consistency over extensive contexts, covering long-term constraints in character settings, event causality, spatial rules, and worldviews. Existing methods compress these heterogeneous elements into homogeneous representations, creating a topological mismatch that lowers retrieval signal-to-noise ratios and induces long-range logical collapse. We propose Topo-Narrator, a framework built on two complementary decouplings. Heterogeneous Topological Memory (HTM) organizes narrative state into a Character Graph, a Plot Chain, and an Environment Tree, providing topology-specific inductive biases. Plan-Reason-Write (PRW) multi-agent collaboration separates high-level reasoning, memory retrieval, and stylistic realization across dedicated agents. Experiments on MoPS and WritingPrompts show that Topo-Narrator consistently generates coherent narratives averaging over 13,000 words and substantially outperforms strong baselines on HANNA quality and fine-grained consistency metrics, validated by three frontier LLM judges and human evaluation.
%U https://aclanthology.org/2026.aacl-short.59/
%P 923-944
Markdown (Informal)
[Topo-Narrator: Heterogeneous Topological Memory for Long-form Narrative Generation](https://aclanthology.org/2026.aacl-short.59/) (Chen et al., AACL-IJCNLP 2026)
ACL
- Kai Chen, Haoran Zhang, Tian Lan, Zehua Duo, Jiang Li, Guanglai Gao, and Xiangdong Su. 2026. Topo-Narrator: Heterogeneous Topological Memory for Long-form Narrative Generation. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 923–944, Hengqin, China. Association for Computational Linguistics.