Cascaded Inference

Follow this topic Ask about this topic

Latest papers

19 papers2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Oct 7, 2026

System Switch: When Should a Fast Decision Model Stop and Think?

Dual-process agents pair a fast policy with a slow deliberative model. In real-time settings the slow model usually runs continuously; in turn-based agents and robot planners it is invoked on events such as uncertainty or a detected failure. We study a fast learned actor that takes every decision and hands control to a reasoning vision-language model only when a gate opens, while the game keeps running. We use closed-loop Doom and the new open "System One" typed-decision models, served through a common llama.cpp interface. On 900 held-out questions, (i) zero-shot decision models from 0.15B to 9B parameters choose to collect items 1.6-1.8 times more often than chance among their errors, in any option order, although the order changes some models' accuracy; (ii) accuracy, calibration and sensitivity (how well confidence separates right from wrong answers) are distinct: models of similar accuracy differ widely in AUROC, and the confidence of the most sensitive one tracks which kinds of situation it fails, not which answers are wrong; (iii) offline, deferring the least confident 30% of decisions to a reasoning model gains over random deferral in proportion to the actor's AUROC (rank correlation 0.87); with actor and rate chosen on held-out games the gain is +0.13 [0.08, 0.18] with doomLaya's option order and +0.08 [0.02, 0.14] with shuffled options, and reasoning carries about half of it; (iv) in closed loop (33 games, three seeds) no variant reaches the exit. Committing to plans, the reasoner's or a fixed explore rule's, opens more doors and makes an actor that stands still play; with the rule the agent dies more often. Told that some doors need keys, the reasoner takes ordinary doors for locked ones, which the state cannot tell apart; without that knowledge it goes back to collecting. We release code, prompts, data and logs.

Gian Luca Bailo

Independent Researcher, Recco (Genoa), Italy

Cascaded Inference LLM Decision-Making Selective Prediction VLM Reasoning Language Model Calibration

Sep 26, 2026

Safety-Constrained Cascade Inference for Robust Malaria Cell Classification Under Field Corruptions

Automated malaria diagnosis from thin blood-smear microscopy could meaningfully reduce the burden on under-resourced laboratories, but a model that maximises accuracy on clean laboratory images fails badly the moment an inexpensive smartphone camera introduces sensor noise. This paper introduces MalariaCascade, a two-stage inference system in which a lightweight MobileNetV2 sentinel (2,225,153 parameters) makes confident classifications at low compute cost and escalates uncertain cases to an EfficientNet-B3 expert (10,697,769 parameters) that sees only clean, standardised images regardless of how corrupted the incoming frame is. Structural isolation of the expert stage, not learned robustness, is the mechanism. The sentinel is trained under a safety-score objective that places an explicit floor on Recall(Parasitised) (>=0.95) and Recall(Uninfected) (>=0.40) before precision is optimised, ensuring the checkpoint satisfies clinical safety constraints by construction. On the NIH Malaria Cell Images Dataset (27,558 cells), the cascade reaches Accuracy=0.9736, Recall(Parasitised)=0.9570, Precision(Parasitised)=0.9912, F1=0.9738, and AUROC=0.9955 on the clean test set. Under Gaussian sensor noise at full severity, cascade Recall(Parasitised) degrades by only 2.4 pp (0.9570 to 0.9329), while the flat single-model baseline collapses by 63.0 pp (0.9584 to 0.3281). McNemar's test confirms the cascade improvement is statistically significant (chi^2=11.14, p=0.00085). An ablation isolating the structural property shows that routing clean images to the expert is responsible for a 16.8 pp Recall(Parasitised) advantage under sensor noise relative to a cascade where the expert also sees corrupted inputs.

J. T. Hagbe, Michel Emel

African School of Economics, Abomey-Calavi, Benin · African Institute for Mathematical Sciences (AIMS), Cameroon

Cascaded Inference Medical Image Classification Classification Image Classification

Sep 10, 2026

Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration

Heterogeneous model collaboration seeks to exploit the complementary strengths of different models to balance predictive performance and inference cost. Existing approaches typically rely either on trained routers, which tie routing decisions to a fixed task and model pool, or on raw-confidence cascades, whose thresholds lack consistent reliability semantics across heterogeneous models. Consequently, these approaches adapt poorly to changing model pools and deployment budgets. We propose Calibration-Aware Uncertainty Cascades (CAUC), a simple post-hoc framework that independently calibrates each model's confidence and selects deployment policies using validation data. The resulting calibrated confidence scores establish a common reliability scale for accepting an early prediction, invoking a stronger model, or selectively combining model outputs. This unified decision criterion decouples deployment policies from any particular model pool or operating budget. We further show theoretically that calibration gives confidence thresholds an explicit selective-risk interpretation, whereas uncalibrated scores offer no comparable reliability guarantee. Extensive experiments demonstrate that, across six language benchmarks, CAUC achieves an average relative accuracy improvement of 1.9% over strong-model-only inference while avoiding approximately 47% of strong-model calls. On image classification benchmarks, it maintains or improves predictive performance while reducing measured GFLOPs by up to 57%.

Yilin Zhang, Han Jiang, Cai Xu +2

School of Computer Science and Technology, Xidian University Xi’an, China

Selective Prediction Cost-Aware Inference Cascaded Inference Uncertainty Calibration

Sep 7, 2026

Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM Inference

Large language model (LLM) cascades answer easy requests with a small model and escalate selected requests to a larger model. Most routers prioritize examples on which the small model appears uncertain or likely to be wrong. This proxy ignores a decisive fact: escalation is useful only when the large model corrects the small model, and it is harmful when the large model replaces a correct answer with an incorrect one. We introduce Signed Rescue Routing (SRR), a budgeted routing method that predicts these two events separately and ranks requests by their difference. We show that this signed conditional gain is the Bayes-optimal routing score under a fixed escalation budget. SRR requires only the small model's output statistics at deployment and adds a lightweight two-head router. We evaluate SRR with Qwen3-4B and Qwen3-8B on TBD examples from MMLU, HellaSwag, and ARC-Challenge. Across the accuracy-compute curve, SRR reaches an area of TBD, compared with TBD for a learned small-model error predictor and TBD for entropy routing. These results show that predicting incremental value, rather than model uncertainty, is a simple and effective objective for efficient LLM cascades.

Zheyuan Wang, Siyu Li, Peiqiao Song +3

School of Artificial Intelligence, Beijing Normal University · School of Information Science and Engineering, Chongqing Jiaotong University · School of Computer Science and Technology, Dalian University of Technology +1

LLM Inference Efficiency LLM Routing Cascaded Inference Language Model Cascading

Sep 1, 2026

Cheap Verifiers, Large Blind Spots: Measuring the Reliability Cost of Cost-Saving Cascades

Inference cascades cut cost by answering most queries with a cheap model and escalating a hard tail to a frontier model that acts as verifier. A natural extension closes the loop: fine-tune the cheap student on the verifier's rejections so the escalation rate, and cost, fall each round. We measure this loop on real LLMs and report four findings. First, the verifier's blind spot, the fraction of the student's wrong answers it accepts, is large and moves adversarially: it grows with student capability (

β

from 0.12 to 0.55 as the student scales 0.5B to 32B) and shrinks with verifier capability, so it is worst in the cheap-student, cheap-verifier regime cascades exist to create. Second, buying it away returns the saving: a frontier verifier drives

β

to about 0.05 but then escalates on 46% of hard-MATH queries against a 39% true error rate, paying the frontier price on nearly half of all traffic. Third, naive corrective fine-tuning on the verifier-rejected tail does not improve the small student but degrades and ultimately collapses it, across every teacher we tried (cross-family and same-family), so at this scale the self-improving loop is self-defeating. Fourth, through all of this the cascade's own dashboard, every metric computed through the verifier, reads a flat 3% error while true delivered error swings up to 32%: the system is blind to its own degradation by construction. We then give the theory that explains the blindness, a two-population conservation law,

ε_\infty \lesssim q_0 β_0

, under which every in-loop metric improves while true quality does not, and a synthetic study that validates the mechanism. The practical conclusion: the reliability of a self-improving cascade cannot be read from any metric computed through its own verifier.

Dushyant Rajput, Nirdesh Chauhan, Siddharth Kosaraju

AltSlate Labs LLP

LLM Inference Efficiency LLM Answer Verification Self-Training LLM Reliability Language Model Cascading Cascaded Inference

Aug 16, 2026

RLCascadeRouter: Quality-Estimator-Free Cascade Routing via Reinforcement Learning

The growing ecosystem of large language models (LLMs) offers huge potential to optimize performance-cost trade-offs. However, their heterogeneous capabilities and inference costs make efficiently routing queries a significant challenge. Existing paradigms are inflexible: one-shot routers commit before observing responses, whereas conventional cascades stop adaptively but follow a fixed model order. Cascade routing removes both restrictions by reconsidering whether to stop or invoke another model after each response. Current methods use a predict-then-optimize pipeline estimating response quality and future model utility. However, prediction loss for quality or utility is not equivalent to routing-decision loss. A lower prediction error does not necessarily yield a better action; a small boundary-crossing error can reverse a

stop'' or model-selection decision. Therefore, we propose RLCascadeRouter, a quality-estimator-free framework that formulates cascade routing as a Markov decision process with actions comprising

stop'' and model selection. It uses trajectory returns and advantages to directly optimize the performance-cost objective. Its Cascade Policy Network models candidate complementarity for model selection and remaining-action value for stopping, eliminating independent post-hoc response-quality estimators. Evaluated across ten LLMRouterBench benchmarks with thirteen LLMs, RLCascadeRouter outperforms strong baselines and achieves superior performance-cost trade-offs. It incorporates unseen models without retraining, and ablation studies validate both policy components.

Shihong Huang, Shengjie Wang, Hong Ma +1

Polytechnic Institute, Zhejiang University, Hangzhou, China · Department of Logistics and Maritime Studies, Faculty of Business, The Hong Kong Polytechnic University, Hong Kong, China

LLM Routing Language Model Cascading Cascaded Inference LLM Inference Efficiency

Aug 7, 2026

CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing

Test-time scaling is often implemented by spending more compute along one axis: sampling more solutions, extending a chain of thought, or applying a stronger evaluator. Under a fixed inference budget, these choices compete. This paper formulates test-time reasoning as a compute-allocation problem in which a system must decide whether the next unit of compute should be spent on generation, verification, or stopping. We introduce CoBa, a compute-balanced routing policy that first obtains a small set of candidates, applies cheap verification broadly, and routes uncertain or high-value candidates to stronger verification. On 3,129 example-generator evaluations spanning MATH-500, AIME 2024/2025, AMC 2023, and procedural symbolic reasoning, CoBa-Routed-Strong reaches 85.13% macro accuracy, statistically matching a self-evaluation weighted-voting proxy at 85.20% while using 49.1% fewer parameter-weighted tokens. It also matches best-of-16 majority voting within 0.01 macro-accuracy points while using 58.9% fewer parameter-weighted tokens; paired tests retain a small best-of-16 edge at substantially higher cost. Paired bootstrap tests show significant gains over single-sample decoding, while the remaining gap to the pool oracle exposes headroom for sharper routing. For local reasoning systems, test-time scaling becomes a question of where the next computation is most valuable.

Yan Zhou, Yue Ouyang, Kaiyang Zheng +1

School of Mathematics and Statistics, Changsha University of Science and Technology, Changsha, China · School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.

Cost-Aware Inference Test-Time Scaling Cascaded Inference Inference-Time Compute Allocation Algorithmic Reasoning

Aug 3, 2026

CARE: A Cascaded Framework for Efficient and Reliable Time Series Anomaly Detection

While deep learning models have achieved state-of-the-art performance in time series anomaly detection, their complex architectures incur substantial inference overhead. Existing methods typically apply a uniform inference strategy across all data points, which is inefficient given that anomalies are inherently scarce and the vast majority of temporal data consists of predictable normal patterns. To mitigate this bottleneck, we propose CARE, a model-agnostic cascaded inference framework that integrates a Lightweight Pre-filter Model (LPM) with an existing high-capacity Complex Detection Model (CDM). The LPM rapidly filters high-confidence normal samples using a Residual MLP AutoEncoder and a Normality-Conditioned Gating mechanism. Crucially, we introduce a Structure Attention module to explicitly capture channel-wise anomaly contributions, and optimize the gating network via a confidence-guided selective routing objective that learns reliable routing decisions to reduce unnecessary CDM invocations. Extensive experiments across eight real-world benchmarks demonstrate that CARE effectively isolates high-confidence normal samples. By routing only uncertain samples to the CDM, our framework achieves

2.7\times

to

4.8\times

inference speedup compared to the most accurate SOTA approaches, while still maintaining competitive detection quality.

Zemin Chao, Qianhui Xu, Jianhe Cen +3

Massive Data Computing Lab, Harbin Institute of Technology

Efficient Neural Network Inference Cost-Aware Inference Cascaded Inference Time-Series Anomaly Detection

Jul 28, 2026

Safety-Aware Cascaded Inference for Crop Damage Assessment with Controlled Error Trade-offs

In picture-based agricultural insurance for smallholder farmers, missed damage detections carry substantially higher cost than false alarms: a farmer who sustained real losses receives no payout, while unnecessary expert review is operationally costly but reversible. Standard multi-class classifiers optimize global accuracy but provide no mechanism to operationalize or control this asymmetric cost structure at inference time. We propose CascadeCropNet, a two-stage cascade architecture calibrated to satisfy a target recall constraint (Rec-Damaged >= 0.95) through threshold selection. A lightweight Sentinel model performs binary health triage; samples exceeding a calibrated damage probability threshold tau are escalated to a specialist Expert model for fine-grained diagnosis. This design provides explicit, deployment-time control over the safety-efficiency trade-off without retraining. Evaluated on the Eyes on the Ground dataset (23,804 images from Kenyan smallholder maize farms), the cascade achieves Rec-Damaged = 0.974 at tau = 0.5, reducing missed damage cases by up to 54% relative to a flat baseline. Under evaluation alignment, the representational gap reduces to +0.008 F1-macro, confirming the contribution is architectural rather than representational. Under input degradation, the system prioritizes escalation over confident misclassification, reflecting error containment through architectural isolation rather than intrinsic model robustness. These results demonstrate that cascade architectures can operationalize safety-oriented decision constraints through calibrated routing in settings where reliability matters more than aggregate accuracy. These properties depend on threshold calibration and deployment conditions and do not constitute guarantees under arbitrary distribution shift.

José Thiéry Messigbédé Hagbe, Gani Kawsar Gounou, Songbian Karim Zimé

aAfrican School of Economics, www.africanschoolofeconomics.com, Abomey Calavi, Benin

Agricultural Image Analysis Agricultural Remote Sensing Cost-Aware Inference Cascaded Inference

Jul 27, 2026

Conformal Cascade: Distribution-Free Accuracy Guarantees for Multi-Tier LLM Inference

Large language model (LLM) cascades reduce inference cost by routing easy queries to a small model and deferring hard queries to a larger one. Production cascades govern this deferral through a confidence threshold, but LLM confidence scores are miscalibrated, the threshold must be tuned per model pair and per domain, and no setting yields a formal bound on cascade accuracy. We introduce Conformal Cascade (CC), a multi-tier inference framework that uses conformal prediction set size as the deferral rule: accept when the calibrated set collapses to a single answer, defer otherwise. The procedure delivers a distribution-free, finite-sample accuracy guarantee. By a per-tier union bound, the prediction set at the accepting tier covers the correct answer with probability at least

1 - Kα

for any user-specified

α

; under a selection-preservation condition (consistent with, but not strictly implied by, our marginal coverage results), the bound tightens to

1 - α

. We further characterise expected cascade cost as an explicit function of

α

and the calibration-set acceptance rate. Across 18 multiple-choice benchmarks spanning science, medicine, commonsense, and standardized exams, evaluated on two-tier cascades drawn from four open-weight model families, CC strictly improves over the strongest calibration-tuned heuristic cascade on the majority of family--benchmark pairs, with the largest gains on reasoning-heavy benchmarks where majority vote is unreliable; on easier benchmarks the cascade commits the vast majority of queries to the small model at no accuracy cost. Extension to open-ended generation requires an answer-clustering step that we leave for future work. The method requires no model training and only black-box API access.

Yifan Dou, Shikan Lian, Shibo Li

Department of Computer Science, Florida State University

LLM Inference Efficiency LLM Inference Scheduling Conformal Prediction Cascaded Inference Language Model Cascading

Jun 25, 2026

Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving

Efficient deployment of large language models (LLMs) in production forces a trade-off between accuracy and cost. Operators often default to a single model that is either expensive for easy queries or insufficient for hard ones. To address this challenge, we propose a two-stage cascaded solution. Stage 1 clusters incoming queries and assigns each cluster to its most cost-effective model. The cost budget for this routing process is set by an interpretable hyperparameter, tuned offline. Stage 2 adds a quality estimation (QE) cascade; when an output from Stage 1 is judged low-quality, the query is escalated to a stronger model. This ensures only hard or low-confidence cases reach the expensive models. On the test datasets, the cascaded system retains 97-99% of the strongest model's accuracy while reducing Time Per Output Token (TPOT). It requires only task-correctness labels and adapts to changes in the model pool without manual reconfiguration.

Yasmin Moslem, Magdalena Kacmajor, Vasudevan Nedumpozhimana +11

1ADAPT Centre, Trinity College Dublin · 2Huawei Research

LLM Serving Cost-Aware Inference LLM Routing Language Model Cascading Cascaded Inference

Jun 17, 2026

SAFE-Cascade: Cost-Adaptive Vision-Language Routing for Chart Question Answering

Vision-language models (VLMs) are powerful for chart question answering, but invoking a VLM for every query can be unnecessarily expensive when many questions are answerable from OCR text and lightweight language reasoning. We demonstrate SAFE-Cascade, an interactive system for cost-adaptive chart question answering. Given a chart image and a natural-language question, SAFE-Cascade first extracts chart text with OCR, obtains a provisional answer from a text-only language model, and then uses a learned router to decide whether to accept the text answer or escalate to a VLM. The demo exposes this decision process to users: OCR evidence, text-only answer, routing probability, escalation decision, final answer, estimated cost, and estimated latency are shown side by side. SAFE-Cascade is designed as a transparent interface for understanding when visual grounding is actually needed. Users can upload or select charts, ask questions, inspect the evidence used by each pathway, compare text-only and VLM answers, and adjust the escalation threshold to explore the accuracy-cost frontier. The system is implemented with Azure Document Intelligence for OCR, gpt-5-mini as the text-only model, gemini-2.5-flash-image as the VLM, and a Random Forest router trained on inference-time features. On a held-out ChartQA test split of 375 examples from a 2,500-example experiment, SAFE-Cascade achieves 69.1% unified accuracy with 73.1% VLM invocation, compared with 67.7% accuracy and 100% VLM invocation for the full-VLM baseline. The observed +1.4 percentage-point difference is statistically uncertain, so we interpret SAFE-Cascade as matching full-VLM performance while reducing VLM calls by 26.9% and estimated cost by 9.3%. The demonstration shows how selective modality routing can make multimodal knowledge systems more transparent, tunable, and cost-aware.

Ayush Dwivedi, Qixin Wang, Ashvi Soni +5

Walmart USA · University of Arkansas USA

Multimodal Understanding Efficient VLM Inference Chart QA Visual Question Answering Multimodal Foundation Models Language Model Cascading+1

Jun 13, 2026

Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades

While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive. MLLM cascades mitigate this cost by first querying a weak but cheaper model and deferring to a strong model when the weak model's output is unconfident. However, since the weak model's confidence directly controls compute allocation, these systems expose a new attack surface: an adversary can manipulate confidence so that their queries are consistently deferred to the strong model. Motivated by this vulnerability, we introduce the Forced Deferral Attack (FDA), an adversarial image attack that lowers the weak model's confidence and causes cascades to route queries to the strong model. FDA learns a universal border trigger by optimizing a temperature-flattened objective. This objective pushes the weak model's token distribution on triggered inputs toward less concentrated targets constructed from its clean responses. Across datasets, model families, and deferral metrics, FDA consistently increases strong-model routing while outperforming image-perturbation and prompt-injection baselines. These results show that MLLM cascades are vulnerable to attacks that manipulate compute allocation, forcing unintended strong-model usage without directly targeting answer correctness.

Zhongye Liu, Yaopei Zeng, Yurui Chang +1

Pennsylvania State University

Adversarial Perturbations Multimodal Robustness LLM Routing Multimodal Foundation Models Adversarial Attacks on VLMs Language Model Cascading+1

May 12, 2026

CADS: Conformal Adaptive Decision System for Cost-Efficient Image Classification

While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environmental impact, and a "one-size-fits-all" approach that ignores varying sample complexity. In clinical settings for instance, the waste of computational resources on routine cases is a significant barrier to sustainable AI. In this paper, we introduce the Conformal Adaptive Decision System (CADS), a sequential multi-model algorithm designed to optimize resource allocation by efficiently sampling models based on the estimated data complexity. CADS leverages conformal prediction to quantify image uncertainty at runtime. CADS provides a mathematically grounded framework for balancing the cost-accuracy dilemma that dynamically routes samples through a model cascade, ranging from lightweight "Scout" models to high-capacity "Oracle" architectures. Validated on two datasets, CADS demonstrated superior efficiency and accuracy at a computational cost that can be up to 12 times lower than heavy-model inference. By accurately routing samples based on real-time complexity, CADS ensures high diagnostic reliability while drastically reducing the economic and environmental footprint of AI.

Mikael Turkoglu, Tim Bary, Vincent Thielens +2

1ICTEAM, UCLouvain, Belgium · 2SAFiR Lab, Univ. of Sherbrooke, Canada · 3Univ. of Mons, Belgium

Adaptive Inference Cost-Aware Inference Cascaded Inference Image Classification

May 11, 2026

UCCI: Calibrated Uncertainty for Cost-Optimal LLM Cascade Routing

LLM cascades and model routing promise lower inference cost by sending easy queries to a small model and escalating hard ones to a large model, but most deployed routers use uncalibrated confidence scores and require per-workload threshold tuning. We present UCCI, a calibration-first router that maps token-level margin uncertainty to a per-query error probability via isotonic regression and selects the escalation threshold by constrained cost minimization. Under three explicit assumptions, threshold policies on the calibrated score are cost-optimal, and isotonic calibration achieves O(n^{-1/3}) sample complexity for expected calibration error (ECE). On a production named entity recognition workload of 75,000 queries served by 4B and 12B instruction-tuned LLMs on H100 GPUs, UCCI cuts inference cost by 31% (95% CI: [27%, 35%]) at micro-F1 = 0.91 while reducing ECE from 0.12 to 0.03. At the same operating point, UCCI beats entropy thresholding, split-conformal routing, and a FrugalGPT-style learned threshold. All cascade results use end-to-end routing on actual model outputs and measured H100 latency, not simulated routing from global accuracies or nominal API prices.

Varun Kotte

Independent Researcher.

Cost-Aware Inference Language Model Calibration LLM Uncertainty Estimation LLM Routing Cascaded Inference

May 7, 2026

Is Escalation Worth It? On the Depth of LLM Cascades

LLM cascades, in which a cheap model defers to an expensive one on low-confidence queries, are widely used to reduce inference cost. Given a pool of models, a practitioner must decide how many models to include and where to set each deferral threshold. We derive first-order optimality conditions showing that, at an optimum, the ratio of expected accuracy gain to expected downstream cost is equal across deferral boundaries. A local search based on these conditions closely matches exhaustive search. We also derive an identity that decomposes the accuracy gain of score-based escalation over random escalation into two AUROC terms. Across five benchmarks and nine deferral scores, with model sequences and thresholds optimized from a pool of eight models, two-model cascades improve mean test-set accuracy over single-model selection by 2.1 to 8.2 percentage points. However, allowing more than two models does not improve mean test-set accuracy in 118 of 135 comparisons across scorers, datasets, and depth caps, and adds at most 0.43 percentage points. To understand the role of deferral scores in depth gains, we conduct counterfactual experiments with simulated confidence scores. When these scores have high AUROC and reflect only whether the current model answered correctly, allowing more than two models improves test-set accuracy on four of five benchmarks. However, these gains do not persist when the scores also reflect query difficulty shared across models, even at the same AUROC. These results suggest that gains from additional depth depend on how well the confidence score separates correct from incorrect answers for the current model compared with later models.

Dylan Bouchard

Cost-Aware Inference LLM Routing Cascaded Inference Language Model Cascading

Apr 1, 2026

Streaming Model Cascades for Semantic SQL

Modern data warehouses extend SQL with semantic operators that invoke large language models on each qualifying row, making per-row inference orders of magnitude more expensive than traditional SQL. Model cascades reduce this cost by routing most rows through a fast proxy model and delegating uncertain cases to an expensive oracle. Prior SUPG-style cascades, however, require a global proxy-score pass that is itself an LLM-inference workload and blocks output in pipelined query engines. They also target either precision or recall and cannot serve workloads that need both. We formalize the cascade routing problem for streaming semantic SQL with independent parallel workers and present two complementary algorithms within this model. SUPG-IT extends SUPG from single-pass, single-metric estimation to streaming execution by iteratively refining two thresholds as oracle labels accumulate across batches, and is the first streaming cascade with joint probabilistic guarantees on user-specified precision and recall at a chosen failure probability

δ

. GAMCAL replaces user-specified targets with a single tradeoff parameter

α

between classification error and oracle cost, and learns a monotone Generalized Additive Model that calibrates proxy scores to true-positive probabilities and supplies pointwise uncertainty for stochastic routing. On six classification, filtering, and join benchmarks evaluated in a production semantic SQL engine, both algorithms reach

F_1 \geq 0.95

at their best operating points. GAMCAL also leads all six datasets at a 20% delegation budget and reaches

F_1 \geq 0.95

with up to 58% fewer oracle calls than LOTUS's SUPG cascade. SUPG-IT attains the highest best-case

F_1

, with a mean of 0.989 across the six datasets.

Paweł Liskowski, Kyle Schmaus

Snowflake Inc. · Poznań, Poland · San Francisco, CA, USA

Cost-Aware Inference LLM Routing Streaming Algorithms Cascaded Inference Language Model Cascading Database Systems

Feb 23, 2026

Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference

We observe that LLM cascading and routing implicitly solves an anytime computation problem -- a class of algorithms, well-studied in classical AI, that improve solutions as additional computation is allocated. We formalize this connection and propose Pyramid MoA, a hierarchical Mixture-of-Agents architecture governed by a decision-theoretic router that escalates queries only when necessary. We establish a Probabilistic Anytime Property with provable monotonicity guarantees and derive a generalized escalation rule from Value of Computation theory that accounts for imperfect oracles, extending the Hansen-Zilberstein monitoring framework to stochastic LLM inference. On MBPP, the router intercepts 81.6% of bugs; on GSM8K/MMLU, the system nearly matches the 68.1% Oracle baseline while achieving up to 42.9% compute savings. The router transfers zero-shot to unseen benchmarks: matching Oracle accuracy on HumanEval (81.1%) and MATH 500 (58.0%) with significant cost reductions. We further discover a context-conditioned anchoring effect across four benchmarks: passing correct SLM reasoning improves Oracle accuracy by up to +19.2pp, while incorrect reasoning degrades it by up to -18.0pp, revealing a fundamental tension in hierarchical MoA architectures.

Arindam Khaled

Independent Researcher

LLM Routing Cost-Aware Inference Multi-Agent LLMs Anytime-Valid Inference Cascaded Inference

Feb 6, 2024

FlowWise: Stateful Fast-Slow Model Serving for Streaming Traffic Intelligence

Network traffic analysis in cloud and internet service provider (ISP) networks increasingly relies on machine learning (ML) models, as encryption and service consolidation make rule-based classification unreliable. At high flow-arrival rates, however, new flows can arrive faster than end-to-end analysis pipelines can process. Unlike typical cloud inference workloads, packets from the same flow arrive over time and require per-flow state. This streaming, stateful setting limits naive scale-out with stateless workers. This paper presents FlowWise, a serving system for streaming, stateful flow intelligence on commodity CPU/GPU servers that jointly selects (i) how many packets to collect and (ii) which model(s) to apply for each flow to balance latency, service rate, and accuracy. Across three representative tasks, inference time across candidate models differs by 1.8x-141.3x, while packet waiting time can exceed feature computation and inference by 6-8 orders of magnitude at the tail. FlowWise exploits these gaps with an uncertainty-driven fast-slow cascade: it issues early predictions from a one-packet model and escalates only uncertain flows to slower models that wait for additional packets and use richer features. A queue-centric runtime maintains per-flow state, performs asynchronous feature joining, and uses brokered, flow-ID-keyed streams to distribute workload across heterogeneous workers. FlowWise serves 76.3% of flows within 16 ms, improving median end-to-end serving latency by 40.5x while increasing service rate and maintaining similar accuracy to always running the slow model. With thousands of packet-header features per flow, our scale-up benchmark sustains over 48.5k new flows per second on a single 16-core commodity CPU server, comparable to reported flow-arrival rates in city-backbone traces. FlowWise is open sourced at https://github.com/noise-lab/FlowWise.

Shinan Liu, Ted Shaowang, Gerry Wan +4

University of Chicago, Chicago, IL, USA · Stanford University, Stanford, CA, USA

Cascaded Inference Efficient Neural Network Inference Encrypted Network Traffic Analysis