{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:37:54Z","timestamp":1761176274035,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Large Language Model (LLM) based multi-agent systems have shown impressive performance across various fields of tasks, further enhanced through collaborative debate and communication using carefully designed communication topologies. However, existing methods typically employ a fixed number of agents or static communication structures, requiring manual pre-definition, and thus struggle to dynamically adapt the number of agents and topology simultaneously to varying task complexities. In this paper, we propose Adaptive Graph Pruning\u00a0(AGP), a novel task-adaptive multi-agent collaboration framework that jointly optimizes agent quantity (hard-pruning) and communication topology (soft-pruning). Specifically, our method employs a two-stage training strategy: firstly, independently training soft-pruning networks for different agent quantities to determine optimal agent-quantity-specific complete graphs and positional masks across specific tasks; and then jointly optimizing hard-pruning and soft-pruning within a maximum complete graph to dynamically configure the number of agents and their communication topologies per task. Extensive experiments demonstrate that our approach is: (1)\u00a0High-performing, achieving state-of-the-art results across six benchmarks and consistently generalizes across multiple mainstream LLM architectures, with a increase in performance of 2.58% \u223c 9.84%; (2)\u00a0Task-adaptive, dynamically constructing optimized communication topologies tailored to specific tasks, with an extremely high performance in all three task categories (general reasoning, mathematical reasoning, and code generation); (3)\u00a0Token-economical, having fewer training steps and token consumption at the same time, with a decrease in token consumption of 90%+; and (4)\u00a0Training-efficient, achieving high performance with very few training steps compared with other methods. The performance will surpass the existing baselines after about ten steps of training under six benchmarks. Our code and demos are publicly available at\u00a0https:\/\/resurgamm.github.io\/AGP\/.<\/jats:p>","DOI":"10.3233\/faia251326","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:58:25Z","timestamp":1761127105000},"source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Graph Pruning for Multi-Agent Communication"],"prefix":"10.3233","author":[{"given":"Boyi","family":"Li","sequence":"first","affiliation":[{"name":"Zhejiang University \u2013 University of Illinois Urbana-Champaign Institute"}]},{"given":"Zhonghan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, College of Computer Science and Technology"}]},{"given":"Der-Horng","family":"Lee","sequence":"additional","affiliation":[{"name":"Zhejiang University \u2013 University of Illinois Urbana-Champaign Institute"}]},{"given":"Gaoang","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University \u2013 University of Illinois Urbana-Champaign Institute"},{"name":"Zhejiang University, College of Computer Science and Technology"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:58:26Z","timestamp":1761127106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251326","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}