CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference

• URL: http://arxiv.org/abs/2605.12001v1
• Date: Tue, 12 May 2026 11:50:15 GMT
• Title: CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference
• Abstract summary: Large language models (LLMs) move from centralized clouds to mobile edge environments.<n> query-level routing between lightweight on-device models and stronger edge models provides a flexible mechanism to navigate this trade-off.<n>Existing routers are designed for centralized cloud settings and optimize token-level costs, failing to capture the dynamic latency and energy overheads in wireless edge deployments.
• Score: 52.849509991178884
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As large language models (LLMs) move from centralized clouds to mobile edge environments, efficient serving must balance latency, energy consumption, and accuracy under constrained device-edge resources. Query-level routing between lightweight on-device models and stronger edge models provides a flexible mechanism to navigate this trade-off. However, existing routers are designed for centralized cloud settings and optimize token-level costs, failing to capture the dynamic latency and energy overheads in wireless edge deployments. In this paper, we formulate mobile edge LLM routing as a deployment-constrained, cost-aware decision problem, and propose CR^2, a two-stage device-edge routing framework. CR^2 decouples a lightweight on-device margin gate from an edge-side utility selector for deferred queries. The margin gate operates on frozen query embeddings and a user-specified cost weight to predict whether local execution is utility-optimal relative to the best edge alternative under the target operating point. We further introduce a conformal risk control (CRC) calibration procedure that maps each operating point to an acceptance threshold, enabling explicit control of the marginal false-acceptance risk under the full-information utility reference. Experiments on the routing task show that CR^2 closely matches a full-information reference router using only device-side signals before deferral. Compared with strong query-level baselines, CR^2 consistently improves the deployable accuracy-cost Pareto frontier and reduces normalized deployment cost by up to 16.9% at matched accuracy.

Related papers

• ConsRoute:Consistency-Aware Adaptive Query Routing for Cloud-Edge-Device Large Language Models [7.869130026927]
  ConsRoute is a lightweight, semantic-aware, and adaptive routing framework for large language models.<n>We show that ConsRoute achieves near-cloud performance (>=95%) while reducing end-to-end latency and inference cost by nearly 40%.
  arXiv  Detail & Related papers  (2026-03-22T13:54:12Z)
• Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization [58.59491516762626]
  We propose AMRO-S, an efficient and interpretable routing framework for Multi-Agent Systems (MAS)<n>AMRO-S models MAS routing as a semantic-conditioned path selection problem, enhancing routing performance through three key mechanisms.<n>Extensive experiments on five public benchmarks and high-concurrency stress tests demonstrate that AMRO-S consistently improves the quality--cost trade-off over strong routing baselines.
  arXiv  Detail & Related papers  (2026-03-13T12:26:05Z)
• RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models [23.345746575717545]
  We formulate LLM routing as the $$-VOR problem to minimize expected set size while controlling the misrouting risk.<n>We propose RACER, extending base routers to output model sets that can be subsequently aggregated for improved output.<n>We theoretically prove that RACER achieves rigorous distribution-free risk control on unseen test data in a post-hoc and model-agnostic manner.
  arXiv  Detail & Related papers  (2026-02-20T08:23:03Z)
• Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems [54.916243942641444]
  Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications.<n>We study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline.
  arXiv  Detail & Related papers  (2025-12-23T03:10:09Z)
• Cost-Aware Contrastive Routing for LLMs [57.30288453580456]
  We introduce Cost-Spectrum Contrastive Routing (CSCR), a lightweight framework that maps both prompts and models into a shared embedding space.<n>CSCR consistently outperforms baselines, improving the accuracy-cost tradeoff by up to 25%.
  arXiv  Detail & Related papers  (2025-08-17T20:16:44Z)
• On-Device LLM for Context-Aware Wi-Fi Roaming [4.8099196240978275]
  Roaming in Wireless LAN (Wi-Fi) is a critical yet challenging task for maintaining seamless connectivity in dynamic mobile environments.<n>We introduce the first cross-layer use of an on-device large language model (LLM): high-level reasoning in the application layer.
  arXiv  Detail & Related papers  (2025-05-07T07:04:49Z)
• Reliability-Optimized User Admission Control for URLLC Traffic: A Neural Contextual Bandit Approach [4.958511942948984]
  Ultra-reliable low-latency communication (URLLC) is the cornerstone for a broad range of emerging services in next-generation wireless networks. URLLC relies on the network's ability to proactively determine whether sufficient resources are available to support the URLLC traffic. New machine learning based method is proposed that builds on (deep) neural contextual bandits.
  arXiv  Detail & Related papers  (2024-01-05T20:26:08Z)
• Adaptive Federated Pruning in Hierarchical Wireless Networks [69.6417645730093]
  Federated Learning (FL) is a privacy-preserving distributed learning framework where a server aggregates models updated by multiple devices without accessing their private datasets. In this paper, we introduce model pruning for HFL in wireless networks to reduce the neural network scale. We show that our proposed HFL with model pruning achieves similar learning accuracy compared with the HFL without model pruning and reduces about 50 percent communication cost.
  arXiv  Detail & Related papers  (2023-05-15T22:04:49Z)
• Structure-aware reinforcement learning for node-overload protection in mobile edge computing [3.3865605512957457]
  This work presents an adaptive admission control policy to prevent edge node from getting overloaded. We extend the framework to work for node overload-protection problem in a discounted-cost setting. Our empirical evaluations show that the total discounted cost incurred by SALMUT is similar to state-of-the-art deep RL algorithms.
  arXiv  Detail & Related papers  (2021-06-29T18:11:41Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.