Adaptive Model Routing

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 63

All topics

False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift
Oct 1, 2026Amit Singh Bhatti, Vishal VaddinaLLM Safety Benchmarks Distribution Shift Robustness
Quantiphi Analytics
FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing
Sep 29, 2026Wang Wei, Harry Yang, Tiankai Yang +6Adaptive Model Routing LLM Routing
Virginia Tech · Independent Researcher · University of Southern California +2
AssayRouter: Historical Utility Priors for Frozen Molecular Predictor Routing
Sep 29, 2026Dong Xu, Zhangfan Yang, Jiantao Wu +5Adaptive Model Routing Task Transferability Estimation
School of Artificial Intelligence, Shenzhen University · EasternDawn · School of Computer Science, University of Nottingham Ningbo
AdaST: Adaptive Coupling for Spatial-Temporal Forecasting
Sep 28, 2026Zhenyu Lei, Chenghao Liu, Yushun Dong +2Adaptive Model Routing Spatiotemporal Forecasting
University of Virginia Charlottesville, VA, USA · Datadog Paris, France · Florida State University Tallahassee, FL, USA +1
Should This Case Be Adapted? Prediction Fragmentation Controls Test-Time Adaptation
Sep 17, 2026Lili Wang, Jing Li, Xiaowen Sun +5Test-Time Adaptation Adaptive Model Routing
Beyond the Query: Do Retrieval Signals Improve Adaptive Multimodal RAG Routing?
Sep 14, 2026Qiaomu Li, Qiuyuan Zhang, Nong MingMultimodal RAG Adaptive Model Routing
College of Computing and Software Engineering Kennesaw State University Marietta, GA 30060, USA
RouteRelay: Event-Triggered Cross-Layer Route Reuse for Efficient Dynamic Sparse Attention
Sep 7, 2026Bin Li, Sisi Liu, Chenyang Hu +3Adaptive Model Routing Efficient Attention
Department of Computer Science, Xiamen University of Technology · School of Mathematics and Computer Science, Fuzhou University
MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification
Aug 13, 2026Daniel Perkins, John Squires, Janou Milligan +2Adaptive Model Routing Ensemble Learning
University of Tennessee, Knoxville · The Bredesen Center for Interdisciplinary Research and Graduate Education
SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks
Aug 12, 2026Tao Yu, Yifei Qu, Zhiqing Cui +14Adaptive Model Routing Cost-Aware Inference
1CASIA · 3NUS · 2UCAS +1
Pre-Inference Routing for Cost-Efficient Document Field Extraction
Aug 6, 2026Sreerekha RajendranAdaptive Model Routing Document Information Extraction
Independent Researcher Salt Lake City, Utah, United States
SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization
Aug 4, 2026Boyao Wang, Zhihan LeiParameter-Free Mixture-of-Experts Routing Adaptive Model Routing
Machine Learning Department Carnegie Mellon University
When Efficiency Becomes Fragility: Exploiting Dynamic Routing Vulnerabilities in Adaptive UAV Tracking
Aug 4, 2026Shaofeng Liang, Runwei Guan, Wenshuo Chen +7Adaptive Model Routing Adversarial Attacks
The Hong Kong University of Science and Technology (Guangzhou) · Wuhan University · Institute of Deep Perception Technology (JITRI)
Uncertainty Is Not Enough: Value-of-Information Routing for Mixtures of LoRA Experts
Aug 3, 2026Tom Saliencro, Rohan Desai, Priya Nair +2Adaptive Model Routing Selective Prediction
University of California, Irvine · University of Washington
Shared Prefixes, Better Credit: Adaptive Routing for Multi-Agent Reasoning
Aug 3, 2026Yiqing Liu, Zihao Wang, Hantao Yao +2Adaptive Model Routing Multi-Agent Collaboration
University of Science and Technology of China
CARNet: Channel-Adaptive Receiver Network for Robust NextG Communications
Aug 3, 2026Chao Jiang, Zhuo Xu, Yongli YanAdaptive Model Routing 6G Networks
Department of Electronic Engineering and the State Key Laboratory of Space Network and Communications, Tsinghua University, Beijing 100084, China
Beyond Routing Saturation: A Long-Horizon Class-Incremental Perspective on Expert Routing in Multimodal Continual Instruction Tuning
Aug 2, 2026Huiyu Yi, Yongqi Xu, Bogang Zhang +5Class-Incremental Learning Adaptive Model Routing
School of Artificial Intelligence, Nanjing University, China · National Key Laboratory for Novel Software Technology, Nanjing University, China
How Often Should a Recommender Call an LLM? Value-Weighted Routing, Monitoring, and Seasonal Robustness
Jul 27, 2026Bhavtosh RathAdaptive Model Routing Cost-Aware Inference
USA
VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrieval
Jul 20, 2026Yu-Chien Tang, Jun-Chen Hung, Wen-Chih Peng +1LLM Inference Efficiency Adaptive Model Routing
National Yang Ming Chiao Tung University · Department of Computer Science Hsinchu, Taiwan
A Multi-Agent System for 5G Throughput Prediction in Multi-Operator Urban Environments
Jul 18, 2026Muhammad Kabeer, Rosdiadee Nordin, Nadiva Nuriftitah +1Adaptive Model Routing Wireless Communications
Faculty of Engineering and Technology, Sunway University, Selangor, Malaysia · Department of Computer Science, Federal University Dutsinma, Katsina, Nigeria · Future Cities Research Institute (FCRI), Faculty of Engineering and Technology, Sunway University, No. 5, Jalan Universiti, Bandar Sunway, 47500 Selangor Darul Ehsan, Malaysia +1
RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation
Jul 10, 2026Kaiji Zhou, Vladimir Kalmykov, Yue FengAdaptive Model Routing Recommender Systems
University of Birmingham Birmingham, United Kingdom
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
Jul 9, 2026Fangxu Yu, Tao Feng, Dehai Min +3Adaptive Model Routing Time Series Reasoning
University of Maryland, College Park · University of Illinois Urbana-Champaign · University of Illinois Chicago +1
Adaptive Inference Batching using Policy Gradients
Jul 6, 2026Ruslan SharifullinEfficient Inference Adaptive Model Routing
Department of Computer Science Stanford University
Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing
Jul 6, 2026Babak Barazandeh, Subhabrata Majumdar, Vinay Prithyani +1Adaptive Model Routing Low-Rank Adaptation
Fortinet · Indian Institute of Management Bangalore · Citadel Securities +1
FedSPM: Routing-Enabled Federated Learning under Dual Heterogeneity via Semiparametric Mixture
Jul 5, 2026Zijian Wang, Pengfei Li, Guangyu Yang +1Latent Variable Models Adaptive Model Routing
Institute of Statistics and Big Data, Renmin University of China · Department of Statistics and Actuarial Science, University of Waterloo
RES-DARE: Failure-Aware Expert Adaptation and Rollback-Safe Self-Repair for Intrusion Detection
Jul 2, 2026Rahil Aftab, Anyash Prasad, Soumya Mazumdar +2Adaptive Model Routing Continual Learning
Engineering Science Homi Bhabha National Institute Anushaktinagar, Mumbai 400094, Maharashtra, India Computer and Informatics Group Variable Energy Cyclotron Centre 1/AF, Bidhannagar, Kolkata 700064, West Bengal, India
Expected Gain-based Escalation in Vertical Federated Learning
Jun 30, 2026Mohamad Mestoukirdi, Vincent CorlayAdaptive Model Routing Multi-View Learning
Mitsubishi Electric R&D Centre, Rennes, France
Budget-Adaptive Routing: Skipping the Weak When the Strong Answers Anyway
Jun 29, 2026Wei Geng, Nitinder Mohan, Jörg OttAdaptive Model Routing Edge Inference
Technical University of Munich Munich, Germany · TU Delft Delft, Netherlands
Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning
Jun 29, 2026Yinan Zhou, Haokun Lin, Yichen Wu +7Efficient Multimodal Inference Adaptive Model Routing
Xi’an Jiaotong University · ARC Lab, Tencent IEG · City University of Hong Kong +3
EntroRouter: Learning Efficient Model Routing via Entropy Regulation
Jun 28, 2026Kaiyi Zhang, Xueliang Zhao, Zhuocheng Gong +2Adaptive Model Routing Cost-Aware Inference
Gaoling School of Artificial Intelligence, Renmin University of China · Ant International · The University of Hong Kong +1
To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG
Jun 23, 2026Jungseob Lee, Chanjun Park, Heuiseok LimRetrieval-Augmented Generation Adaptive Model Routing
Korea University · Soongsil University

Oct 1, 2026, cs.CRJ/K move · Enter open · S save

False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift

Amit Singh Bhatti, Vishal Vaddina

Quantiphi Analytics

LLM Safety Benchmarks Distribution Shift Robustness Adaptive Model Routing Language Model Safety Evaluation Selection Bias

Open paper AskPDF arXiv

Safety routers send each request to one of several models and are judged against the best single model. A major routing benchmark picks that comparator on the evaluation data. In the benchmark's own setting this is harmless, but under distribution shift it is not. On HELM Safety the selection cost is 0.003-0.030 of harm under random splits and 0.045-0.113 under held-out categories, comparable to the whole deficit attributed to routing, with its direction holding under either published judge alone. It rises seven- to ninefold on AgentDojo when suites are held out. Across seven safety corpora chosen by rules fixed in advance, three meet a registered interval test and four beat a later permutation null, and three of the four interval misses are corpora where some models have zero observed harm. Prior work proves the direction of this bias. We size it on harm and accuracy, show that it is larger under the held-out splits we measure, and bound it by optimism plus a shift-dependent regret. Scored honestly under shift, routing buys little on these benchmarks. In most pool cells the nested router serves the honest baseline's model, and on the nearly saturated AgentDojo corpus a perfect pre-dispatch router is worth at most two points of harm. We also find a model's expressed recognition of a late injection steerable. On held-out reruns an attacker who knows which model it faces lowers GPT-5.4's judged recognition by 19.6 points, confirmed by an independent label. In an offline counterfactual composition into a controller, the same attack raises or lowers estimated harm depending on the fallback model. Safety routing should be evaluated under shift, against a baseline chosen without the test labels, and recognition-based defences should be scored on harm against an attacker who chooses what the model sees.

Momentum

Related topics

Latest papers 63