From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification

2026-03-28 · Huamin Chen, Xunzhuo Liu, Bowei He, Xue Liu arxiv

The Semantic Router DSL is a non-Turing-complete policy language deployed in production for per-request LLM inference routing: content signals (embedding similarity, PII detection, jailbreak scoring) feed into weighted projections and priority-ordered decision trees that select a model, enforce privacy policies, and produce structured audit traces -- all from a single declarative source file. Prior work established conflict-free compilation for probabilistic predicates and positioned the DSL within the Workload-Router-Pool inference architecture. This paper extends the same language from stateless, per-request routing to multi-step agent workflows -- the full path from inference gateway to agent orchestration to infrastructure deployment. The DSL compiler emits verified decision nodes for orchestration frameworks (LangGraph, OpenClaw), Kubernetes artifacts (NetworkPolicy, Sandbox CRD, ConfigMap), YANG/NETCONF payloads, and protocol-boundary gates (MCP, A2A) -- all from the same source. Because the language is non-Turing-complete, the compiler guarantees exhaustive routing, conflict-free branching, referential integrity, and audit traces structurally coupled to the decision logic. Because signal definitions are shared across targets, a threshold change propagates from inference gateway to agent gate to infrastructure artifact in one compilation step -- eliminating cross-team coordination as the primary source of policy drift. We ground the approach in four pillars -- auditability, cost efficiency, verifiability, and tunability -- and identify the verification boundary at each layer.

📄 PDF Abstract BibTeX arXiv:2603.27299

Code (0)

등록된 구현이 없습니다.

Declarative Skills for AI Agents in Knowledge-Grounded Tool-Use Workflows

2026-06-05 · M. Danish Lim, I. Danial Bin Sharudin, Wen Han Chen, Cedric Lim 외 arxiv

We study orchestration mechanisms for tool-using AI agents in realistic customer-service workflows over an unstructured knowledge base. We argue that declarative agents -- AI agents equipped with natural-language skill f…

Context Kubernetes: Declarative Orchestration of Enterprise Knowledge for Agentic AI Systems

2026-04-13 · Charafeddine Mouzouni arxiv

We introduce Context Kubernetes, an architecture for orchestrating enterprise knowledge in agentic AI systems, with a prototype implementation and eight experiments. The core observation is that delivering the right know…

IslandRun: Privacy-Aware Multi-Objective Orchestration for Distributed AI Inference

2025-11-29 · Bala Siva Sai Akhil Malepati arxiv

Modern AI inference faces an irreducible tension: no single computational resource simultaneously maximizes performance, preserves privacy, minimizes cost, and maintains trust. Existing orchestration frameworks optimize …

Federated Learning

Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation

2026-05-06 · Zhiqing Cui, Haotong Xie, Jiahao Yuan, Cheng Yang 외 arxiv

Large language model (LLM) multi-agent systems typically rely on rigid orchestration, committing either to flat per-query routing or to hand-engineered task decomposition, so decomposition depth, worker choice, and infer…

CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing

2026-01-27 · Shanyv Liu, Xuyang Yuan, Tao Chen, Zijun Zhan 외 arxiv

Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tasks. We propose CASTE…