arXiv：cs.AI· Hehai Lin, Zixuan Wang, Ming Yan, Peidong Wang, Shilei Cao, Minzhi Li, Bosheng Ding, Juepeng Zheng, Chengwei Qin·· 16 小时前
MAS-Gate：以节点为中心的量化打通多智能体系统全生命周期
MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification
AI 导读
研究者提出 MAS-Gate，一种以节点为中心的统一量化方法，将 LLM 多智能体系统的开发与运行刻画为设计时编排、运行时干预、事后归因三阶段生命周期。该方法把每次执行建模为有向无环图，结合节点内效用与节点间强度，分别用于 Orchestrator 训练的密集奖励、基于配对奖励训练 Editor 编辑执行前缀，以及为 LLM 事后归因提供按风险排序的节点证据。
正文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.17613 [cs.AI] |
| (or arXiv:2610.17613v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17613 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hehai Lin [view email]
[v1]
Tue, 13 Oct 2026 02:33:28 UTC (304 KB)
来源：arXiv：cs.AI · arxiv.org