MA-RWG: A Multi-Agent Framework for Thematically Structuring and Generation of Related Work

Liu, Zhuang; Liu, Jian; Kang, Chun; Zhang, Chenbin; Li, Rui; Zeng, Fanhu; Dai, Yong; Sha, Lei

doi:10.24963/ijcai.2026/656

MA-RWG: A Multi-Agent Framework for Thematically Structuring and Generation of Related Work

Zhuang Liu, Jian Liu, Chun Kang, Chenbin Zhang, Rui Li, Fanhu Zeng, Yong Dai, Lei Sha

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 5892-5900.

https://doi.org/10.24963/ijcai.2026/656

Keywords

Natural Language Processing: Information retrieval and text mining
Agent-based and Multi-agent Systems: Applications
Natural Language Processing: Summarization
Natural Language Processing: Language generation

Abstract

AI-driven survey generation has advanced rapidly, yet related work generation (RWG) remains relatively underexplored. Unlike surveys that provide broad literature overviews, RWG synthesizes prior studies for a single focal paper, requiring contextual fit, cross-paper comparison, and accurate attribution. To address this gap, we propose MA-RWG, a fully automated multi-agent framework that generates polished related work sections from only a title and abstract. MA-RWG first retrieves high-quality candidate papers through semantic retrieval, optionally enhanced with a diversity-aware term. It then coordinates four specialized agents for summarization, organization, integration, and fact checking, enabling DAG-based taxonomy construction, feedback-guided refinement, and dual-model verification. For evaluation, we introduce a dedicated benchmark for paper-specific related work generation, covering generation quality, citation quality, and claim-level semantic similarity. Experimental results show that MA-RWG outperforms RAG-based baselines and survey-oriented agentic methods on the RWG task. Further ablation and cross-domain experiments demonstrate the soundness and robustness of the proposed framework.

Zhuang Liu, Jian Liu, Chun Kang, Chenbin Zhang, Rui Li, Fanhu Zeng, Yong Dai, and Lei Sha. 2026. MA-RWG: A Multi-Agent Framework for Thematically Structuring and Generation of Related Work. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 5892–5900. https://doi.org/10.24963/ijcai.2026/656

@inproceedings{ijcai2026p656,
  title     = {MA-RWG: A Multi-Agent Framework for Thematically Structuring and Generation of Related Work},
  author    = {Liu, Zhuang and Liu, Jian and Kang, Chun and Zhang, Chenbin and Li, Rui and Zeng, Fanhu and Dai, Yong and Sha, Lei},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {5892--5900},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/656},
  url       = {https://doi.org/10.24963/ijcai.2026/656},
}

TY  - CPAPER
TI  - MA-RWG: A Multi-Agent Framework for Thematically Structuring and Generation of Related Work
AU  - Liu, Zhuang
AU  - Liu, Jian
AU  - Kang, Chun
AU  - Zhang, Chenbin
AU  - Li, Rui
AU  - Zeng, Fanhu
AU  - Dai, Yong
AU  - Sha, Lei
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 5892
EP  - 5900
DO  - 10.24963/ijcai.2026/656
UR  - https://doi.org/10.24963/ijcai.2026/656
ER  -