# Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems

arXiv: https://arxiv.org/abs/2512.20012 · HTML: https://mlsanity.com/paper/2512.20012/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 46 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Builds on (most cited first, 27 of 27)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification](https://mlsanity.com/paper/2305.09781/) (2023)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control](https://mlsanity.com/paper/2110.01052/) (2021)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement](https://mlsanity.com/paper/2407.18370/) (2024)
- [EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference](https://mlsanity.com/paper/2011.14203/) (2020)
- [Reasoning Models Better Express Their Confidence](https://mlsanity.com/paper/2505.14489/) (2025)
- [TeleQnA: A Benchmark Dataset to Assess Large Language Models Telecommunications Knowledge](https://mlsanity.com/paper/2310.15051/) (2023)
- [Generative AI Agents with Large Language Model for Satellite Networks via a Mixture of Experts Transmission](https://mlsanity.com/paper/2404.09134/) (2024)
- [Interactive AI with Retrieval-Augmented Generation for Next Generation Networking](https://mlsanity.com/paper/2401.11391/) (2024)
- [A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directions](https://mlsanity.com/paper/2412.19823/) (2024)
- [ORAN-Bench-13K: An Open Source Benchmark for Assessing LLMs in Open Radio Access Networks](https://mlsanity.com/paper/2407.06245/) (2024)
- [Thought calibration: Efficient and confident test-time scaling](https://mlsanity.com/paper/2505.18404/) (2025)
- [Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection](https://mlsanity.com/paper/2409.15844/) (2024)
- [Discriminative Estimation of Total Variation Distance: A Fidelity Auditor for Generative Data](https://mlsanity.com/paper/2405.15337/) (2024)
- [Rational Tuning of LLM Cascades via Probabilistic Modeling](https://mlsanity.com/paper/2501.09345/) (2025)
- [Leveraging Large Language Models for Collective Decision-Making](https://mlsanity.com/paper/2311.04928/) (2023)
- [Quantile Learn-Then-Test: Quantile-Based Risk Control for Hyperparameter Optimization](https://mlsanity.com/paper/2407.17358/) (2024)
- [Ensuring Reliability via Hyperparameter Selection: Review and Advances](https://mlsanity.com/paper/2502.04206/) (2025)
- [Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty?](https://mlsanity.com/paper/2509.04464/) (2025)
- [Covert Prompt Transmission for Secure Large Language Model Services](https://mlsanity.com/paper/2504.21311/) (2025)
- [Evaluating Open-Source Large Language Models for Technical Telecom Question Answering](https://mlsanity.com/paper/2509.21949/) (2025)

## Built on by (most cited first, 2 of 2)

- [Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents](https://mlsanity.com/paper/2607.26865/) (2026)
- [CoVStream: Edge-Cloud Collaboration for Understanding of Long Video Streams](https://mlsanity.com/paper/2606.22804/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications, assisting with tasks including troubleshooting, standards interpretation, and network optimization. However, their deployment in practice must balance inference cost, latency, and reliability. In this work, we study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline. In it, an efficient edge model handles routine queries, a more capable cloud model addresses complex cases, and human experts are involved only when necessary. We define a misalignment-cost constrained optimization problem, aiming to minimize average processing cost, while guaranteeing alignment of automated answers with expert judgments. We propose a statistically rigorous threshold selection method based on multiple hypothesis testing (MHT) for a query processing mechanism based on knowledge and confidence tests. The approach provides finite-sample guarantees on misalignment risk. Experiments on the TeleQnA dataset -- a telecom-specific benchmark -- demonstrate that the proposed method achieves superior cost-efficiency compared to conventional cascaded baselines, while ensuring reliability at prescribed confidence levels.