🤖 AI Summary
This work addresses the limitations of manually crafted static assume-guarantee contracts in cross-domain deterministic networking, which struggle to adapt to dynamic traffic and lack automated synthesis mechanisms. The paper presents the first framework that integrates large language models with formal verification to automatically synthesize both static and dynamic cross-domain contracts. Leveraging a large language model as a reasoning agent and combining network calculus, packet-level simulation, or real-world testbeds as verification oracles, the approach enables typed network modeling and precise determination of safe reconfiguration points. Evaluated on a TDM-PON infrastructure, the framework successfully generates dynamic 5G fronthaul contracts meeting a 100-microsecond deadline, achieving 3.5× higher bandwidth efficiency than static over-provisioning schemes with only 1.2 microseconds of latency error, while seamlessly supporting static 5G-TSN bridging scenarios.
📝 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.