arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.17613cs.AIcs.MA
收藏

MAS-Gate:通过以节点为中心的量化解锁多智能体系统生命周期

MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification

The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Sun Yat-sen University(中山大学);Nanyang Technological University(南洋理工大学);National University of Singapore(新加坡国立大学)

Hehai Lin, Zixuan Wang, Ming Yan, Peidong Wang, Shilei Cao, Minzhi Li, Bosheng Ding, Juepeng Zheng, Chengwei Qin

AI总结:

该研究提出统一以节点为中心的量化方法MAS-Gate,适配MAS生命周期三阶段,在多任务场景下优于阶段特定基线,可改进MAS生成、编辑与错误归因。

摘要:

基于大语言模型(LLM)的多智能体系统(MAS)可通过分解任务、协调互补能力解决单个智能体无法处理的复杂问题。尽管MAS研究广泛,但现有工作多聚焦于其开发或运行的特定方面或阶段,导致视角碎片化,不同场景下的目标与信号难以协调。为弥合这些脱节视角,本文将MAS的开发与运行概念化为包含执行前的设计时编排、执行中的运行时干预、执行后的事后归因三个阶段的生命周期,并提出适用于所有阶段的统一以节点为中心的量化方法MAS-Gate。该方法将每次执行建模为有向无环图,结合节点内效用(通过参考答案似然的变化估计节点贡献)与节点间强度(近似语义吸收及潜在下游影响)。我们将该共享量化方法适配三个目标:为Orchestrator训练提供结构感知的密集奖励;利用已编辑与未编辑轨迹的配对奖励训练Editor,使其能对执行前缀进行操作;为基于LLM的事后归因提供风险排序的节点作为辅助证据。在交互环境、知识密集型多跳问答、通用推理及事后归因上的实验表明,MAS-Gate在工作流构建、针对性运行时编辑、LLM辅助错误定位方面优于对应阶段特定的基线方法。综上,这些结果确立了MAS-Gate作为统一结构接口,可在整个生命周期中改进MAS生成、动态编辑与错误归因。

英文摘要:

Large language model (LLM)-based multi-agent systems (MAS) can solve complex problems beyond the reach of a single agent by decomposing tasks and coordinating complementary capabilities. Despite extensive research on MAS, existing work largely focuses on specific aspects or individual phases of their development and operation, resulting in fragmented perspectives with objectives and signals that are difficult to reconcile across these different settings. To bridge these disconnected perspectives, we conceptualize MAS development and operation as a three-phase lifecycle spanning design-time orchestration before execution, runtime intervention during execution, and post-hoc attribution after execution, and introduce MAS-Gate, a unified node-centric quantification applicable across these phases. Modeling each execution as a directed acyclic graph, MAS-Gate combines within-node utility, which estimates a node's contribution through changes in reference-answer likelihood, with inter-node strength, which approximates semantic uptake and potential downstream reach. We adapt this shared quantification to three objectives: providing a structure-aware dense reward for Orchestrator training, training an Editor to act on execution prefixes using paired rewards from completed edited and unedited trajectories, and supplying risk-ranked nodes as auxiliary evidence for LLM-based post-hoc attribution. Experiments spanning interaction environments, knowledge-intensive multi-hop question answering, general reasoning, and post-hoc attribution demonstrate that MAS-Gate improves workflow construction, targeted runtime editing, and LLM-assisted error localization over corresponding phase-specific baselines. Together, these results establish MAS-Gate as a unified structural interface for improving MAS generation, dynamic editing, and error attribution throughout the lifecycle.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑