提出时空旁路机制，让智能体路由系统自动识别拓扑结构并防范故障级联扩散。
Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switching
- 设计双分型评分器：欧氏评分处理密集环状结构，双曲评分捕捉树状结构的指数风险。
- 在250个场景中，系统成功率从50.4%提升至87.2%，树状结构下提升达48~68个百分点。
- 仅133参数的小门控网络即可准确判断拓扑几何，适合部署于实时推理系统。
先进的AI推理系统通过动态执行图中的专用智能体调度任务。我们发现该架构存在结构性盲区：调度器优化负载与性能，却缺乏对故障传播差异的建模能力——在树状结构中，单一故障会呈指数级扩散；而在稠密环状结构中，故障则自我抑制。一个不考虑拓扑几何的调度器无法区分这两种情形。我们将其形式化为在线几何控制问题，并证明：当每边传播概率超过图分支因子倒数时（p > e^{-γ}，γ为BFS壳层增长指数），故障传播进入超临界状态。为此，我们引入一个时空旁路机制，预测当前拓扑更适配何种路由几何。该旁路包含：(i) 欧氏传播评分器，用于稠密环状子图；(ii) 双曲评分器，捕捉树状子图的指数风险；(iii) 一个仅含133参数的可学习门控模块，基于拓扑与几何感知特征融合两者评分。在涵盖五种拓扑区间的250个基准场景中，该方案将原调度器胜率从50.4%提升至87.2%（+36.8 pp）。在树状区域，增益达+48至+68 pp。所学门控模块在留出测试集上达到AUC=0.9247，验证几何偏好可从实时信号中恢复。跨架构验证在Barabasi-Albert、Watts-Strogatz与Erdos-Renyi图上均表明传播建模具有泛化能力。
原文摘要 · Abstract (English)
Advanced AI reasoning systems route tasks through dynamic execution graphs of specialized agents. We identify a structural blind spot in this architecture: schedulers optimize load and fitness but lack a model of how failure propagates differently in tree-like versus cyclic graphs. In tree-like regimes, a single failure cascades exponentially; in dense cyclic regimes, it self-limits. A geometry-blind scheduler cannot distinguish these cases. We formalize this observability gap as an online geometry-control problem. We prove a cascade-sensitivity condition: failure spread is supercritical when per-edge propagation probability exceeds the inverse of the graph's branching factor (p > e^{-γ}, where γis the BFS shell-growth exponent). We close this gap with a spatio-temporal sidecar that predicts which routing geometry fits the current topology. The sidecar comprises (i) a Euclidean propagation scorer for dense, cyclic subgraphs, (ii) a hyperbolic scorer capturing exponential risk in tree-like subgraphs, and (iii) a compact learned gate (133 parameters) that blends the two scores using topology and geometry-aware features. On 250 benchmark scenarios spanning five topology regimes, the sidecar lifts the native scheduler's win rate from 50.4% to 87.2% (+36.8 pp). In tree-like regimes, gains reach +48 to +68 pp. The learned gate achieves held-out AUC = 0.9247, confirming geometry preference is recoverable from live signals. Cross-architecture validation on Barabasi-Albert, Watts-Strogatz, and Erdos-Renyi graphs confirms propagation modeling generalizes across graph families.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。