{"type":"ScholarlyArticle","title":"MA-RWG: A Multi-Agent Framework for Thematically Structuring and Generation of Related Work","authors":[{"name":"Zhuang Liu","slug":"zhuang-liu","given":"Zhuang","family":"Liu","affiliation":""},{"name":"Jian Liu","slug":"jian-liu","given":"Jian","family":"Liu","affiliation":""},{"name":"Chun Kang","slug":"chun-kang","given":"Chun","family":"Kang","affiliation":""},{"name":"Chenbin Zhang","slug":"chenbin-zhang","given":"Chenbin","family":"Zhang","affiliation":""},{"name":"Rui Li","slug":"rui-li","given":"Rui","family":"Li","affiliation":""},{"name":"Fanhu Zeng","slug":"fanhu-zeng","given":"Fanhu","family":"Zeng","affiliation":""},{"name":"Yong Dai","slug":"yong-dai","given":"Yong","family":"Dai","affiliation":""},{"name":"Lei Sha","slug":"lei-sha","given":"Lei","family":"Sha","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/656","url":"https://ijcai.org/proceedings/2026/656","pdf":"https://ijcai.org/proceedings/2026/0656.pdf","markdown":"https://ijcai.org/proceedings/2026/656.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/656","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Natural Language Processing","track":"Main Track","number":656,"pages":{"first":5892,"last":5900},"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"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}