{"ID":2830175,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.22137","arxiv_id":"2512.22137","title":"HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference","abstract":"Edge-cloud collaborative inference is becoming a practical necessity for LLM-powered edge devices: on-device models often cannot afford the required reasoning capability, while cloud-only inference could be prohibitively costly and slow under strict latency and token/API budgets. However, existing edge-cloud collaboration methods often route per query or fixed steps simply based-on the estimated difficulty. Such coarse and static heuristics overlook subtask dependencies, missing opportunities for parallel execution and budget-adaptive routing. To this end, we propose \\textbf{HybridFlow}, a resource-adaptive edge-cloud inference framework that (i) builds a dependency-aware DAG for each query and executes newly unlocked subtasks in parallel, reducing end-to-end latency; (ii) routes each subtask online to the edge or cloud via a learned benefit--cost utility model that dynamically trades accuracy gains against token/API and latency budgets, thereby reducing unnecessary cloud usage while preserving reasoning quality. Across GPQA, MMLU-Pro, AIME24, and LiveBench-Reasoning, HybridFlow improves the cost-accuracy trade-off, reducing latency and cloud API usage while maintaining competitive accuracy against strong structured reasoning baselines.","short_abstract":"Edge-cloud collaborative inference is becoming a practical necessity for LLM-powered edge devices: on-device models often cannot afford the required reasoning capability, while cloud-only inference could be prohibitively costly and slow under strict latency and token/API budgets. However, existing edge-cloud collaborat...","url_abs":"https://arxiv.org/abs/2512.22137","url_pdf":"https://arxiv.org/pdf/2512.22137v4","authors":"[\"Jiangwen Dong\",\"Jiayu Li\",\"Tianhang Zheng\",\"Wanyu Lin\"]","published":"2025-12-11T08:35:59Z","proceeding":"cs.DC","tasks":"[\"cs.DC\"]","methods":"[\"Large Language Model\"]","has_code":false}