{"type":"ScholarlyArticle","title":"JURIS: Bringing the Jury System to Multi-Agent Summarization","authors":[{"name":"Ziling Li","slug":"ziling-li","given":"Ziling","family":"Li","affiliation":""},{"name":"Junwei Zhang","slug":"junwei-zhang","given":"Junwei","family":"Zhang","affiliation":""},{"name":"Yixuan Yang","slug":"yixuan-yang","given":"Yixuan","family":"Yang","affiliation":""},{"name":"Yuqiang Han","slug":"yuqiang-han","given":"Yuqiang","family":"Han","affiliation":""},{"name":"Xiaolin Li","slug":"xiaolin-li","given":"Xiaolin","family":"Li","affiliation":""}],"abstract":"Agents implemented using Large Language Models (LLMs) offer novel solutions for tasks such as document summarization. However, single-agent systems, limited by their own knowledge base, often exhibit information omissions or inconsistencies with the facts, while multi-agent systems lacking effective organization can fall into the trap of social cognitive defects such as flattery and premature consensus. Inspired by the U.S. jury system, we propose JURIS, a judicial-decision-inspired multi-agent collaborative framework. Specifically, the document summarization process simulates a lawsuit scenario: multiple generator agents condense the target text into multiple sentences from different perspectives, much like lawyers on both sides providing different evidence; multiple decision-making agents consider the overall picture based on defense and voting mechanisms to select candidate sentences, much like a jury adopting different evidence; finally, a chief editor agent compiles a summary of all selected sentences, much like a secretary summarizing a plan and a judge giving a final verdict. Extensive experiments on in-domain news and cross-domain benchmarks demonstrate that JURIS consistently and significantly outperforms strong single-agent and multi-agent baselines across automatic evaluation metrics, multi-dimensional quality assessments, and human judgments, validating the effectiveness of decision-driven structured multi-agent collaboration for document summarization.","doi":"10.24963/ijcai.2026/23","url":"https://ijcai.org/proceedings/2026/23","pdf":"https://ijcai.org/proceedings/2026/0023.pdf","markdown":"https://ijcai.org/proceedings/2026/23.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/23","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":"Agent-based and Multi-agent Systems","track":"Main Track","number":23,"pages":{"first":199,"last":207},"keywords":["Agent-based and Multi-agent Systems: Other","Agent-based and Multi-agent Systems: Normative systems","Agent-based and Multi-agent Systems: Multi-agent planning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}