AgentGate: A Lightweight Structured Routing Engine for the Internet of Agents
Yujun Cheng, Enfang Cui, Hao Qin, Zhiyuan Liang, Qi Xu

TL;DR
AgentGate introduces a lightweight, structured routing engine for efficient, privacy-aware agent dispatch in the Internet of Agents, formulated as a constrained decision problem with a two-stage process.
Contribution
It proposes a novel two-stage structured routing approach and a routing-oriented fine-tuning scheme for compact models in agent systems.
Findings
Compact models achieve competitive routing performance under constraints.
Model differences mainly affect action prediction and candidate selection.
Structured routing is feasible for resource-constrained, privacy-sensitive agent systems.
Abstract
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 have improved agent naming, discovery, and interaction, efficient request dispatch remains an open systems problem under latency, privacy, and cost constraints. In this paper, we present AgentGate, a lightweight structured routing engine for candidate-aware agent dispatch. Instead of treating routing as unrestricted text generation, AgentGate formulates it as a constrained decision problem and decomposes it into two stages: action decision and structural grounding. The first stage determines whether a query should trigger single-agent invocation, multi-agent planning, direct response, or safe escalation, while the second stage instantiates the selected action into…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
