arXiv AI July 24, 2026 By Evan Chen, Shiqiang Wang, Kevin S Chan, Su Wang, Christopher Brinton

Routing Without Training: Controllable-Ratio LLM Offloading via Reliability Gating

arXiv:2607. 20481v1 Announce Type: new Abstract: Local-cloud collaboration is a practical way to deploy large language models under resource constraints, but existing methods often rely on trained routers or collaboration-aware finetuning that tie routing behavior to a particular operating regime.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 1

Pro-Router: Token-Aware Progressive Model Routing with Adaptive Edge-Cloud Collaboration for Efficient Multimodal LLM Inference

arXiv:2608.28726v1 Announce Type: new Abstract: The remarkable performance of multimodal large language models (MLLMs) comes at the cost of substantial computational overhead, posing significant chal...

By Xinyuan Gui, Shaowen Wang, Sheng Sun, Zijian Wang, Zishu Yu, Zheming Yang

llms efficiency multimodal benchmarks

arXiv Machine Learning

Jul 14

Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversations

arXiv:2502. 11007v5 Announce Type: replace Abstract: Compared to traditional machine learning models, recent large language models (LLMs) can exhibit multi-task-solving capabilities through multi-modal data sources and multi-turn conversations.

By Liangqi Yuan, Dong-Jun Han, Shiqiang Wang, Christopher G. Brinton

llms reinforcement-learning multimodal

arXiv Machine Learning

Sep 22

Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving

arXiv:2609.23085v1 Announce Type: cross Abstract: Large language models (LLMs) and agentic AI systems are creating rapidly growing inference energy demands as model sizes grow and reasoning trajector...

By Muhammad Abdur Rab Siddiqui, Daniela Rojas, Chen Yang, Wenqi Cui, Yuanyuan Shi, Yize Chen

llms agents fine-tuning benchmarks

arXiv AI

4d ago

Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing

arXiv:2609.37362v1 Announce Type: new Abstract: Large language model (LLM) routing aims to assign each query to the most suitable model from a heterogeneous candidate pool, improving the quality--eff...

By Guannan Lai, Han-Jia Ye

llms

arXiv AI

Sep 12

Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration

The paper introduces Calibration-Aware Uncertainty Cascades (CAUC), a post‑hoc framework that calibrates each model’s confidence independently and uses these calibrated scores to decide when to accept an early prediction, invoke a stronger model, or combine outputs. CAUC establishes a common reliability scale across heterogeneous models, decoupling deployment policies from specific model pools or budgets. Experiments on six language benchmarks show a 1.9% relative accuracy gain over strong‑model‑only inference while cutting strong‑model calls by about 47%, and on image classification it maintains or improves performance while reducing GFLOPs by up to 57%.

By Yilin Zhang, Han Jiang, Cai Xu, Ying Liu, Wei Zhao

computer-vision benchmarks

arXiv AI

Aug 5

Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls

arXiv:2608. 03071v1 Announce Type: new Abstract: Large language model agents derive much of their capability from tool use.

By Guoyao Yu, Xiaoqing Sun, Ziqi Huang, Shaojing Fan, Zhongyi Zhang, Xiaomeng Hu, Xiaobo Xue, Yangyang Shi, Xiong Xiao, Yang Song, Biao Lyu, Rong Wen, Xing Li, Qinming He, Shunming Zhu, Zhenguang Liu

llms rag agents fine-tuning benchmarks

One email a morning, machine-written

Related stories

Pro-Router: Token-Aware Progressive Model Routing with Adaptive Edge-Cloud Collaboration for Efficient Multimodal LLM Inference

Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversations

Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving

Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing

Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration

Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls