paper-with-me

홈 › Papers

Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switching

2026-03-17 · Davide Di Gioia arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.17112

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning

2026-05-11 · Ruiyi Yang, Lihuan Li, Hao Xue, Flora D. Salim arxiv

Compositional spatiotemporal reasoning often requires a system to invoke multiple heterogeneous specialists, such as geometric, temporal, topological, and trajectory agents. A central question is how such a system should…

SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading

2025-10-04 · Yuanzhe Shen, Yide Liu, Zisu Huang, Ruicheng Yin 외 arxiv

Large language models (LLMs) demonstrate remarkable performance across diverse tasks, yet their effectiveness frequently depends on costly commercial APIs or cloud services. Model selection thus entails a critical trade-…

Dual-Layer Agentic Memory with Fast Write Routing and Slow Consolidation

2026-08-23 · Wenzhi Li, Dong Nie, Rui Lan, Tongtong Lyu 외 arxiv

Large language model (LLM) agents operate in dynamic environments where knowledge continuously evolves. Existing memory systems typically treat external memory as a monotonically growing repository, inevitably leading to…

MasRouter: Learning to Route LLMs for Multi-Agent Systems

2025-02-16 · Yanwei Yue, Guibin Zhang, Boyang Liu, Guancheng Wan 외

Multi-agent systems (MAS) powered by Large Language Models (LLMs) have been demonstrated to push the boundaries of LLM capabilities, yet they often incur significant costs and face challenges in dynamic LLM selection. Cu…

HumanEvalmbpp

AgentGate: A Lightweight Structured Routing Engine for the Internet of Agents

2026-04-08 · Yujun Cheng, Enfang Cui, Hao Qin, Zhiyuan Liang 외 arxiv

The rapid development of AI agent systems is leading to an emerging Internet of Agents, where specialized agents operate across local devices, edge nodes, private services, and cloud platforms. Although recent efforts ha…

Text Generation