Automated Synthesis of Deterministic Cross-Domain Interfaces
2026-08-10 • Networking and Internet Architecture
Networking and Internet Architecture
AI summaryⓘ
The authors address how different network domains agree on traffic and quality guarantees, which are usually made by hand and too cautious. They developed a system that uses large language models (LLMs) to automatically create these contracts for both fixed and changing traffic, verifying them with network simulations. Their method produced efficient and accurate contracts for a 5G network scenario, outperforming traditional static approaches. They also found that LLMs are better at building models than directly calculating exact delays, which require formal tools. The same approach also worked for a different network setup without changes.
Deterministic NetworkingAssume-Guarantee ContractLarge Language ModelsNetwork Calculus5G FronthaulTDM-PONQoS (Quality of Service)Reactive SchedulingNetwork SimulationStatic vs Dynamic Contracts
Authors
Konstantinos Christodoulopoulos, Antonis Selentis-Boulntadakis
Abstract
Deterministic networking spans heterogeneous domains. At each boundary, two domains must agree on an assume--guarantee contract: what traffic the client may inject, and the QoS the carrier will hold for it. Composing such contracts into an end-to-end guarantee is standardized, but deriving each domain's contract is not. Today they are hand-crafted, static, and over-provisioned. The difficulty rises when traffic changes and the contract must become dynamic. We present a framework that automatically synthesizes the per-domain contract for both static and dynamic classes, along with the registration the dynamic one rests on. Two reasoning modules implemented with large language models (LLMs) drive it: an agent takes the client's traffic declaration and searches the carrier's configuration mechanisms, and a handler builds the network model from a typed disclosure of the substrate. The handler calls a network-calculus kernel for the model's hard terms, and an independent oracle---a faithful simulator, testbed, or live network---which verifies each candidate and discovers what lacks an a-priori algebraic form: when a reconfiguration is safe, and the instant to apply it. We synthesized a dynamic contract for uplink 5G fronthaul over a TDM-PON, grounded against a packet-level simulator. Across six draws from two LLM families, every synthesis produced a feasible, verified contract tight to ${\sim}1.2\,μ$s, holding a $100$-$μ$s deadline that reactive scheduling cannot meet, at up to $3.5$ times the bandwidth efficiency of static over-provisioning. Tasked instead with computing the worst-case delay directly, the LLMs were unsound in five of six attempts---evidence for the division of labor: LLMs construct the model, formal tools hold numeric authority. The same framework, unchanged, synthesized a static 5G--TSN bridge contract on a second substrate.