PROTEUS: SLA-Aware Routing via Lagrangian RL for Multi-LLM Serving Systems

• URL: http://arxiv.org/abs/2601.19402v3
• Date: Tue, 03 Feb 2026 09:00:56 GMT
• Title: PROTEUS: SLA-Aware Routing via Lagrangian RL for Multi-LLM Serving Systems
• Abstract summary: We present PROTEUS, a router that accepts accuracy targets tau as runtime input.<n>A single trained model serves the full accuracy spectrum without retraining.<n>We evaluate on RouterBench (11 models, 405K queries) and SPROUT (14 models, 45K queries)
• Score: 1.0978496459260902
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Production LLM deployments serve diverse workloads where cost and quality requirements vary by customer tier, time of day, and query criticality. Model serving systems accept latency SLOs directly. LLM routers do not. They force operators to tune parameters offline and guess what accuracy might result. The relationship between parameters and outcomes is indirect, non-monotonic, and dataset-dependent. Operators need to specify accuracy targets, not infer them from opaque settings. We present PROTEUS (Polymorphic Router for Operational Target Enforcement with Unified SLA), a router that accepts accuracy targets tau as runtime input. PROTEUS uses Lagrangian dual control. A learned dual variable lambda tracks constraint violations during training and conditions the policy network. This lets the router translate specified tau values into routing decisions that satisfy them. A single trained model serves the full accuracy spectrum without retraining.We evaluate on RouterBench (11 models, 405K queries) and SPROUT (14 models, 45K queries). PROTEUS achieves consistent floor compliance where accuracy meets or exceeds tau. The target-response correlation reaches 0.97 to 0.98. The closest baseline, OmniRouter, meets floors only 22% of the time despite also using Lagrangian optimization. PROTEUS operates across tau in [0.85, 0.95] from a single model. On RouterBench it achieves 90.1% accuracy, within 1.3% of oracle. On SPROUT it achieves 94.0% accuracy, within 4.6% of oracle. Cost savings reach 89.8% versus the best fixed model.

Related papers

• LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks [3.789882665982407]
  Multi-agent large language model (LLM) systems can improve reasoning by spending more computation.<n>We isolate this decision by running every problem under four protocols while holding the solver fixed within each setting.
  arXiv  Detail & Related papers  (2026-08-14T22:35:37Z)
• TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI [8.291830023781403]
  We present TRACE, a task-level routing framework that aligns routing with the unit of supervision.<n>By leveraging delayed task feedback, TRACE- learns routing policies that adapt to the workload.<n>It consistently improves the accuracy-matched trade-off, achieving non-latency frontier points.
  arXiv  Detail & Related papers  (2026-07-24T16:29:06Z)
• Influence of Prompt Engineering on Small Language Models for Guarded Query Routing [0.0]
  We investigate whether compact open-weight Small Language Models (SLMs) can jointly handle both tasks under latency constraints.<n>We find that mid-scale SLMs come close to frontier model routing quality at much lower latency.<n>Results show that prompt optimization techniques enable SLMs to handle such cases gracefully, without changing the models' weights.
  arXiv  Detail & Related papers  (2026-07-06T09:21:18Z)
• LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer? [69.71754384259167]
  Multimodal large language models (MLLMs) have heterogeneous strengths across OCR, chart understanding, spatial reasoning, visual question answering, cost, and latency.<n>We propose Latent, a router that formulates MLLM routing as counterfactual multimodal utility prediction.<n> Experiments on MMR-Bench and VL-Bench show that Latent outperforms fixed-model, feature-level, and learned-router baselines.
  arXiv  Detail & Related papers  (2026-05-11T22:42:12Z)
• RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents [91.0187958746262]
  RouteMoA is an efficient mixture-of-agents framework with dynamic routing.<n>It employs a lightweight scorer to perform initial screening by predicting coarse-grained performance from the query.<n>It refines these scores through lightweight self- and cross-assessment based on existing model outputs, providing posterior correction without additional inference.
  arXiv  Detail & Related papers  (2026-01-26T04:22:22Z)
• LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing [44.046399484829635]
  Large language model (LLM) routing assigns each query to the most suitable model from an ensemble.<n>We introduce LLMBench, a large-scale benchmark and unified framework for LLM routing.<n>It comprises over 400K instances from 21 datasets and 33 models.
  arXiv  Detail & Related papers  (2026-01-12T05:01:15Z)
• Dr.LLM: Dynamic Layer Routing in LLMs [55.11953638340419]
  Dr.LLM is a retrofittable framework that equips pretrained models with lightweight per-layer routers deciding to skip, execute, or repeat a block.<n>On ARC (logic) and DART (math), Dr.LLM improves accuracy by up to +3.4%p while saving 5 layers per example on average.
  arXiv  Detail & Related papers  (2025-10-14T17:51:26Z)
• ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers [14.831117443453165]
  Large language model (LLM) query routers are critical to modern AI platforms.<n>We propose Prox, which applies an exponentially tilted aggregation mechanism to balance bias and variance in nonparametric routers.
  arXiv  Detail & Related papers  (2025-10-10T20:28:14Z)
• Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs [69.2486294522259]
  BaRP is a Bandit Routing-feedback with Preferences approach that trains under the same partial-feedback restriction as deployment.<n> Framed as a contextual bandit over prompt features and a user preference vector, our method simulates an online feedback setting during training and adapts its routing decisions to each new prompt.
  arXiv  Detail & Related papers  (2025-10-08T18:24:59Z)
• From Score Distributions to Balance: Plug-and-Play Mixture-of-Experts Routing [52.01745035243826]
  Mixture-of-Experts (MoE) models can scale parameter capacity by routing each token to a subset of experts.<n> conditional routing shifts the burden on inference memory, limiting the number of experts per device.<n>We present LASER, a plug-and-play, inference-time routing algorithm that balances load while preserving accuracy.
  arXiv  Detail & Related papers  (2025-09-29T16:29:17Z)
• RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing [27.481573948464987]
  Radial is a novel framework for large language models routing.<n>It uses a lightweight Transformer-based backbone with a radial structure named RadialFormer to articulate the query-LLMs relationship.<n>It significantly outperforms existing routing methods by 9.2% and 5.8% in the Balance and Cost First scenarios.
  arXiv  Detail & Related papers  (2025-06-04T12:16:41Z)
• Guarded Query Routing for Large Language Models [2.2349474636722317]
  We study a guarded query routing problem, for which we first introduce the Guarded Query Routing Benchmark (GQR-Bench)<n>Our results show that WideMLP, enhanced with out-of-domain detection capabilities, yields the best trade-off between accuracy (88%) and speed (4ms)<n>Our findings challenge the automatic reliance on LLMs for (guarded) query routing and provide concrete recommendations for practical applications.
  arXiv  Detail & Related papers  (2025-05-20T15:46:59Z)
• Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding [74.31981011985681]
  Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution. We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures.
  arXiv  Detail & Related papers  (2024-11-06T22:02:30Z)
• LLM Robustness Against Misinformation in Biomedical Question Answering [50.98256373698759]
  The retrieval-augmented generation (RAG) approach is used to reduce the confabulation of large language models (LLMs) for question answering. We evaluate the effectiveness and robustness of four LLMs against misinformation in answering biomedical questions.
  arXiv  Detail & Related papers  (2024-10-27T16:23:26Z)
• Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch [72.97553348776425]
  We introduce DARE to set most delta parameters without affecting the abilities of Supervised Fine-Tuning (SFT) LMs. Then, we use DARE as a versatile plug-in to sparsify delta parameters of multiple SFT models and merge them into a single model. We also utilize DARE to create a merged LM that ranks first among models with 7 billion parameters on the Open Leaderboard.
  arXiv  Detail & Related papers  (2023-11-06T13:43:07Z)

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.