PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design
Computer Science > Computation and Language arXiv:2610.20628 (cs) [Submitted on 29 Sep 2026] Title:PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design Authors:Phuong Tuan Dat, Qi Li, Xinchao Wang View a PDF of the paper titled PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design, by Phuong Tuan Dat and 2 other authors View PDF HTML (experimental)
计算机科学 > 计算与语言 arXiv:2610.20628 (cs) [提交于 2026 年 9 月 29 日] 标题：PRISM：特权同级引导的多智能体拓扑设计 作者：Phuong Tuan Dat, Qi Li, Xinchao Wang 查看标题为《PRISM：特权同级引导的多智能体拓扑设计》的论文 PDF，作者为 Phuong Tuan Dat 及其他 2 位作者 查看 PDF HTML（实验性）
Abstract:Multi-agent systems (MAS) based on large language models (LLMs) have become a powerful way to address complex problems, and their effectiveness depends critically on the collaboration topology that decides which agents participate and how they communicate. Recent work learns to generate this topology from the task query, fitting the generator to corpora of execution-verified graphs. The post-training method for such generators remains a limitation: a corpus lists the graphs that solved a query but never ranks them, leaving continued supervised fine-tuning (SFT) with no per-query preference to exploit.
摘要：基于大语言模型（LLM）的多智能体系统（MAS）已成为解决复杂问题的强大手段，其有效性关键取决于决定哪些智能体参与以及它们如何通信的协作拓扑。近期的研究学习从任务查询中生成这种拓扑，将生成器拟合到经执行验证的图语料库中。此类生成器的训练后方法仍存在局限性：语料库列出了解决查询的图，但从不对其进行排名，导致持续的监督微调（SFT）缺乏可利用的每查询偏好。
Without such a preference, the generator drifts toward the topologies the corpus contains most often rather than those that suit each query, so a gain on one task can come at a cost on another. We propose PRISM, which recovers per-query signal from the same corpus by learning with privileged information: a teacher reads, through a zero-initialized low-rank branch, a sibling graph that also solved the query and is unavailable at deployment, and the student matches its per-decision targets on trajectories the student samples itself.
由于缺乏这种偏好，生成器会倾向于语料库中出现频率最高的拓扑，而非最适合每个查询的拓扑，因此在一个任务上的收益可能会以牺牲另一个任务为代价。我们提出了 PRISM，它通过利用特权信息进行学习，从同一语料库中恢复每查询信号：教师模型通过一个零初始化的低秩分支，读取一个同样解决了该查询但在部署时不可用的同级图，而学生模型则在自身采样的轨迹上匹配其每项决策的目标。
Across six diverse benchmarks PRISM improves over every topology-design baseline evaluated, and matched-teacher controls support the contribution of privileged query information. Code is available in this link. Subjects: Computation and Language (cs.CL) Cite as: arXiv:2610.20628 [cs.CL] (or arXiv:2610.20628v1 [cs.CL] for this version)
在六个不同的基准测试中，PRISM 优于所有评估的拓扑设计基准，且匹配教师对照实验支持了特权查询信息的贡献。代码可在该链接获取。学科：计算与语言 (cs.CL) 引用方式：arXiv:2610.20628 [cs.CL]（或此版本的 arXiv:2610.20628v1 [cs.CL]）