LLM Routing

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

30 papers in the last four weeks, up 88% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 224

Jun 30, 2026cs.SE

SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks

Large language models (LLMs) embedded in multi-turn agentic harnesses are reshaping software engineering (SWE), but routing every task to a frontier model is wasteful when many issues admit cheap fixes. Existing LLM routers operate on the task description alone, which inherits an information-theoretic Bayes-error floor in agentic settings: a similar issue can hide either a localized typo or a multi-module refactor, and the prompt does not separate the two. We introduce SWE-Router, a value-based temporal approach that lets a cheap model run for a few exploratory turns and reads the resulting partial trajectory before deciding whether to continue cheaply or to escalate to an expensive model. We provide a Bayes-optimality theorem showing that conditioning on the partial trajectory never harms routing and is strictly better whenever exploration is informative. Across the LLM pairs of weak and strong models spanning the contemporary cost--capability frontier, we show that SWE-Router greatly improves the cost efficiency of SWE tasks, while maintaining the majority of the performances of the stronger model. We additionally release a multi-LLM trajectory dataset which allows reproduction of our trajectory-level routing.

Seongho Son, Sangwoong Yoon, Jiahua Tang +3

University College London, United Kingdom · Ulsan National Institute of Science and Technology, South Korea · PSL Research University, France +1

Software Engineering Agents LLM Agent Workflow Optimization LLM Routing LLM Agent Harnesses LLM Agent Routing

Jun 28, 2026cs.DB

SemJoin: Semantic Join Optimization

Integrating unstructured data into relational database systems is increasingly important as demand grows for natural language querying and analysis. A semantic join, joining two tables under a natural-language predicate, can be evaluated with a large language model (LLM), but comparing every pair of tuples requires O(M x N) LLM invocations and is cost-prohibitive at scale. Existing systems reduce this cost but typically commit to a single fixed strategy (e.g., embedding similarity or one batched scheme) regardless of the data or the join predicate. We propose an LLM-agent-based decision pipeline that optimizes semantic joins by matching the execution strategy to the characteristics of the underlying tables. An LLM advisor routes each join to one of two strategies: a Cluster Join, which prunes candidates via unsupervised embedding clustering and sample-based filtering, or a Classifier strategy for predicates that reduce to a shared discrete label set. Across three diverse datasets (IMDb reviews, email contradictions, and Stack Overflow tags), the advisor consistently identifies the optimal execution strategy for each workload. This dynamic routing proves decisive: it outperforms adaptive block join (ABJ) by 20-33 F1 points across all datasets while consuming fewer tokens on two of the three, and achieves higher F1 scores than featurized-decomposition join (FDJ) at one to two orders of magnitude lower token cost.

Christopher Gou, Aditya Banerjee, Jiaxuan Wang +1

Purdue University

Large Language Model-Guided Optimization Cost-Aware Inference LLM Routing

Jun 28, 2026cs.CL

EntroRouter: Learning Efficient Model Routing via Entropy Regulation

Model routing balances solution accuracy and computational cost by selecting among models of varying capabilities. While recent multi-round frameworks interleave reasoning and planning, we identify a structural failure mode termed Trust Region Collapse. We demonstrate that the deep coupling of reasoning and routing, exacerbated by the dominance of strong pre-training priors under sparse supervision, leads to degenerate local optima where capable experts are systematically suppressed. To decouple these processes, we propose

\textbf{EntroRouter}

, a single-round routing framework that treats entropy regulation as a core objective. We first initialize the policy via Soft Supervision, fitting a distribution of suitable models to establish a high-entropy prior for exploration. Subsequently, we stabilize Reinforcement Learning using a Soft Anchor, which utilizes offline capability estimates to orchestrate controlled entropy contraction within a safe trust region. Extensive experiments demonstrate that EntroRouter retains 98.3% of the strongest expert's accuracy while reducing computational costs by 48.25%.

Kaiyi Zhang, Xueliang Zhao, Zhuocheng Gong +2

Gaoling School of Artificial Intelligence, Renmin University of China · Ant International · The University of Hong Kong +1

Adaptive Model Routing Cost-Aware Inference LLM Routing

Jun 28, 2026cs.CL

TriageRA-CCF: Source-Side Clinical Confidence and Coverage Signals for Adaptive Rank Budgeting in Medical LLMs

Medical large language models are commonly adapted with a fixed low-rank budget, even though medical questions differ substantially in confidence, clinical coverage, and cross-domain difficulty. We study adaptive rank budgeting for parameter-efficient medical question answering: for each question, the adapter decides whether to activate a small, medium, or large subset of LoRA rank channels. The central challenge is that a naive adaptive budget router can collapse to unstable choices or spend capacity without improving shifted benchmarks. We propose TriageRA-CCF, a source-side teacher for adaptive rank-budgeted LoRA. It combines three signals computed only from source training data: base-model answer confidence, metadata-cell clinical coverage, and a counterfactual close-miss proxy. These signals supervise a straight-through budget router over active ranks {2,4,8}, together with budget-cost, entropy, and rank-balance regularization. Under a matched CMB-source training protocol, TriageRA-CCF achieves the best average accuracy among LoRA, DoRA, and MoELoRA baselines on both Qwen3-8B and Llama3.1-8B. The gains are modest and non-uniform across benchmarks: +0.21 average points over the strongest external baseline on Qwen3-8B and +0.16 on Llama3.1-8B. Component ablations show that confidence, coverage, and counterfactual signals all provide useful budget supervision, but their combination is not monotonically best on every backbone.

Shucan Ji, Yining Huang, Hongliang Guo

College of Computer Science, Sichuan University, Chengdu, China · Meta Emergence Laboratory

Low-Rank Adaptation Medical QA LLM Routing Adaptive Rank Allocation Medical LLMs

Jun 28, 2026cs.AI

When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning

Chain-of-Thought (CoT) improves large language models (LLMs) on difficult reasoning tasks, but it often incurs long natural-language rationales that are poorly aligned with efficient machine reasoning. We propose Communicative Language Symbolism Routing (CLSR), a test-time framework in which multiple LLM agents autonomously invent, evolve, and share compact Language Symbolism Frameworks (LSFs), while a latent-free router adaptively selects and composes these languages per query to optimize the accuracy-token trade-off. Unlike prompt optimization that refines surface instructions, CLSR treats each LSF as a reusable symbolic protocol with compact symbols, usage rules, and a message-passing contract, and improves it through an evolutionary loop driven by correctness and token cost. At inference time, the router may invoke a single low-cost LSF call, ensemble multiple LSFs, or execute a multi-round LSF composition protocol on harder queries. Across challenging benchmarks, CLSR reduces latency-oriented generated token completion by

3\sim 6\times

compared to standard CoT while maintaining accuracy. We further derive an information-theoretic lower bound on token cost under arbitrary symbolism and show that, under an interpreter-realizability premise, multi-round LSF protocols conditionally subsume program-execution pipelines. Code is publicly available (https://github.com/pzqpzq/LSF_MDia).

Zhengqi Pei, Qingming Huang, Shuhui Wang

State Key Lab of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China. · School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China.

Multi-Agent LLM Systems Efficient Language Model Reasoning LLM Routing Multi-Agent Communication

Jun 25, 2026cs.PF

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

Jun 25, 2026cs.AI

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

Multi-model LLM systems such as routing, voting, cascades, fusion, and mixture-of-agents are used to beat single-model accuracy. We show that their gain is capped by a quantity the field rarely reports. For any policy whose output is one member model answer, accuracy cannot exceed one minus beta, where beta is the rate at which every model is wrong on the same query. In contrast, the usual diagnostic, average pairwise error correlation rho, cannot identify beta: error laws with identical marginals and pairwise correlations can have different all-wrong rates. A Clopper-Pearson bound on beta gives a finite-sample certificate on the largest gain any router, vote, or cascade could deliver before training a router. Across 67 models from 21 providers, a tetrachoric-calibrated single-factor model still underprices the all-wrong tail: on open-ended mathematics, observed beta is 0.052 versus 0.023 under the full 67-model Gaussian copula, about 2.5 times underpricing, with 90 percent CI 1.7 to 3.4 and k equals 17. The effect recurs on execution-graded code, where beta is 0.079. Re-asking the same GPQA-Diamond questions in free-response rather than multiple-choice form reopens the tail, with beta 0.127 and a five-judge panel with kappa 0.73 to 0.92, locating co-failure in answer format rather than subject. At matched quality, low-rho heterogeneous ensembles beat high-rho Self-MoA, but on checkable tasks in our pool, combining models rarely beats the single best model without a strong query-level routing signal. Gains come from models failing on different questions, not from adding more models.

Josef Chen

KAIKAKU

LLM Evaluation LLM Routing Language Model Ensembles

Jun 25, 2026cs.AI

The Capability Frontier: Benchmarks Miss 82% of Model Performance

Existing benchmarks typically report accuracy for a single model on a single run. This systematically understates real-world LLM capabilities, particularly under heterogeneous data distributions: (i) different models get different questions correct according to their specializations, and (ii) given a budget, multiple generations can be sampled and selectively retained. To quantify this gap, we introduce the Capability Frontier: a Pareto frontier over a set of models that characterizes the best achievable performance at each cost level under optimal selection across models and generations (i.e., via an oracle). Our construction corrects for two opposing biases: underestimation from single-model evaluation and overestimation from taking maxima over noisy samples. We study 21 LLMs across 16 widely used benchmarks spanning coding, reasoning, medicine, factuality, instruction following, and agentic tasks, comparing Capability Frontier performance at matched cost to each benchmark's top-performing model. Correcting for single-model evaluation yields a 54% error rate reduction; additionally correcting for single runs yields an 82% improvement, with SOTA accuracy matched at 85% cost reduction. Complementing these empirical results, we use controlled probabilistic simulations to show that higher query topic entropy produces a near-monotonic increase in the performance gap between oracle routing and the best single model. Our findings suggest collective LLM capabilities are substantially underestimated, with implications for evaluation and deployment in data-heterogeneous, multi-domain settings.

Bradley Fowler, Ryan Smith, Daniel Thi Graviet +8

1Martian · 3ThoughtWorks · University of Oxford

LLM Evaluation Language Model Generation Evaluation Test-Time Scaling LLM Routing Language Model Ensembles

Jun 24, 2026cs.CL

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing

Test-time scaling improves language-model reasoning, but existing approaches often face a difficult trade-off: long chain-of-thought sampling remains single-threaded, while sentence- or solution-level search can be computationally expensive and hard to train end-to-end. We introduce Local Branch Routing (LBR), a token-level test-time scaling framework that expands a small local lookahead tree, forwards all sampled branches through the language model, and uses a lightweight router to select the depth-1 subtree to commit. By routing over the hidden states of candidate local futures, LBR allows each token decision to use evidence beyond the root next-token distribution while avoiding full solution-level search. The resulting prune-shift-grow decoding process preserves discrete branch identities and defines a tractable tree-trajectory likelihood: newly grown nodes are counted when first sampled, and router decisions are assigned explicit probabilities. This enables end-to-end reinforcement learning with verifiable rewards, jointly optimizing the base model and router under the same likelihood-ratio principle as discrete-token RLVR. On synthetic hierarchical-planning tasks, LBR shows that post-candidate hidden states provide useful routing evidence. On mathematical reasoning benchmarks, LBR improves both Pass@1 and Pass@32 over discrete chain-of-thought, vanilla discrete-token RLVR, and RL-compatible soft-token branching baselines. These results suggest that lightweight local branching offers an efficient, trainable, and discrete form of language-model test-time scaling.

Yutong Yin, Mingyu Jin, Jin Pan +12

1Northwestern University · 2Rutgers University · University of Wisconsin–Madison +7

RL for Language Model Reasoning Test-Time Scaling Efficient Language Model Reasoning LLM Routing Efficient Language Model Inference LLM Reasoning

Jun 22, 2026cs.AI

DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models

Hybrid reasoning models can answer directly or spend extra tokens on extended thinking. A practical router should choose between these modes for each query, so easy problems avoid unnecessary reasoning and hard problems receive enough budget to finish the answer. Existing routers move in this direction, but they typically require labeled training data or fix thinking budgets up front, ignoring answer-level evidence from the model itself. We introduce DART, a training-free routing framework that samples two cheap no-think drafts, accepts direct answering when the drafts agree, and predicts a thinking budget from draft entropy when they disagree. Across the main comparisons, DART preserves or improves always-thinking accuracy in most settings while reducing thinking-token use. Accuracy improves by up to +9.0 points on Olympiad-level math and by up to +22.5 points on code under execution-based equivalence, while thinking-token use drops by 32-73%. The Stage~1 signal extends across model scales (0.6B--32B), model families, and API-only hosted settings, with no labeled data and no gradient updates required. Our code is available at https://github.com/js-lee-AI/DART.

Jungseob Lee, Seongtae Hong, Seungjun Lee +7

Korea University · 242dot · Konkuk University +3

LLM Routing Efficient Language Model Inference Large Reasoning Models

Jun 22, 2026cs.AI

Agent-as-a-Router: Agentic Model Routing for Coding Tasks

Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all. Consequently, routing each task to the most suitable model becomes critical for both performance and cost. Existing routers treat this as a static, one-off classification problem. However, we identify the performance bottleneck for these routers as information deficit: simply augmenting a vanilla LLM router with performance statistics at the task-dimension level yields a 15.3% relative gain, surpassing a heuristic router built on the same dimension-level priors. Motivated by this finding, we propose Agent-as-a-Router, a framework that formalizes routing as a C-A-F loop (Context->Action->Feedback->Context). It closes the information gap by accumulating execution-grounded experience during deployment. We instantiate this framework as ACRouter, composed of an Orchestrator, a Verifier, a Memory module, and introduce CodeRouterBench, an evaluation environment comprising ~10K task instances with verified scores from 8 frontier LLMs, enabling regret-based router comparison on streaming tasks. Experiments show that ACRouter achieves the lowest cumulative regret on in-distribution tasks and generalizes to out-of-distribution agentic-programming tasks, demonstrating that our routing framework actively closes the information gap. Codes and benchmarks are released at https://github.com/LanceZPF/agent-as-a-router.

Pengfei Zhou, Zhiwei Tang, Yixing Ma +8

1National University of Singapore · 2DAMO Academy, Alibaba Group · 3Hupan Lab +3

AI Coding Agents AI Agent Benchmarks LLM Routing LLM Agent Routing

Jun 22, 2026cs.LG

RLM-Cascade: Response-Level Speculative Decoding for Cost-Efficient LLM API Serving

We present RLM-Cascade, a proxy-layer system that applies speculative decoding at the response level to reduce LLM API costs without requiring model architecture access or a shared vocabulary. A fast, inexpensive draft model generates a candidate response; a capable verify model accepts, enhances, or is bypassed entirely depending on a lightweight complexity router. On a real-world agentic coding workload (Claude Code), RLM-Cascade achieves a draft-use rate of 88.8% across 125 production requests, reducing API cost by 45.8% relative to a direct Opus baseline. Counter-intuitively, the proxy also reduces end-to-end latency: median response time is 2,026 ms versus 3,698 ms for Native Opus -- a 1.83X speedup at p50 -- because the SKIPPED path (DeepSeek only, no Opus call) dominates the workload distribution. Quality matches or exceeds the Opus baseline: 100% pass rate on a 20-task Code/Math/Instruct benchmark versus 95% for Native Opus. We further describe a rule-based complexity router that selects the SKIPPED path for simple agentic turns and a hybrid tool-call strategy that bypasses the speculative pipeline for schema-critical tool-selection turns. RLM-Cascade is deployed in production as an enterprise AI infrastructure component and published as open source with a live metrics dashboard and Prometheus endpoint.

Haifeng Wu, Srinivasan Manoharan, Fangbo Tu +2

PayPal

LLM Inference Serving Speculative Decoding LLM Routing Efficient Language Model Inference

Jun 22, 2026cs.CL

Does the Same Token Mean the Same State? MoE Routing as Signal for Reasoning Control

In sparse Mixture-of-Experts language models, does the same token id imply the same router state and the same experts producing it? Holding the emitted token id fixed at repeated anchors, we find it does not: the experts that produce it still separate task context, trajectory history, and reasoning-effort mode. This residual structure supports test-time control: near \emph{boundary} anchors (the final-response transition) and \emph{delimiter} anchors (which open the answer, e.g.\ \texttt{\textbackslash boxed{} or code fences), routing neighborhoods already align with final-answer basins at a marker-only readout and strongest when the routing is read at the answer opening. We operationalize this as \textbf{RAD} (Routing Agreement Decoding), an answer-string-free multi-rollout selector: it locates a fixed anchor, represents each rollout by its anchor-window MoE routing states, and returns the densest Weighted-Jaccard

K

-NN route-basin center, without parsing, normalizing, executing, or voting over answer strings. Across 10 sparse-MoE configurations (gpt-oss, Qwen3-MoE) and 6 datasets spanning math, GPQA, and code, RAD is on par with Majority where string voting is well-posed, with small positive paired deltas (RAD

73.9

/ RAD+DC

74.2

vs.\ Majority

73.6

). Like majority voting, RAD is not a verifier: a dense \emph{wrong} basin can still win. Its value is the interface: the same selector gives direct pass@1 on code, where exact-string voting is ill-defined, and the same routing-density principle, re-anchored to the agentic boundary, improves best-of-16 patch selection on SWE-bench Verified over random, where patches have no answer string to vote on.

Kang Chen, Minshen Yu, Junjie Nian +3

Fudan University · Shanghai Innovation Institute

Mixture-of-Experts Language Models LLM Routing

Jun 18, 2026cs.LG

Is Our Benchmark Enough? An Analysis of Continual Learning for MLLMs

Continual adaptation is essential for multimodal large language models (MLLMs) deployed across evolving domains, but the state-of-the-art MR-LoRA method highly relies on the assumption that a MLLM-based router is necessary to process complex multimodal inputs. This paper revisits this claim on the MLLM-CL benchmark and argues for two claims. \textbf{First}, routing does not require an MLLM: a simple training-free, replay-free ptotypical routing method (\textsc{RePRo}), uses frozen pretrained features and task prototypes to match the MLLM-based router of MR-LoRA at far lower computational cost. \textbf{Second}, shared experts do not improve continual learning for MLLMs, despite their theoretical appeal. We show that these findings arise from two structural limitations of MLLM-CL: (1) its tasks are \textbf{highly separable} in representation space, and (2) its fixed task order makes conclusions \textbf{sensitive to a single curriculum} rather than robust across diverse continual-learning trajectories. As a result, the benchmark primarily rewards learning in isolation rather than genuine continual transfer. This motivates a new design for future benchmarks of continual MLLM learning, with overlapping task manifolds, multiple task orders, fine-grained domain shifts, and evaluation protocols that reward forward transfer as well as retention.

Van-Tuan Tran, Shruthi Gowda, Merim Dzaferagic +1

School of Computer Science and Statistics, Trinity College Dublin, Ireland · Department of Mathematics and Computer Science, Eindhoven University of Technology, The Netherlands

Continual Learning LLM Routing Continual Learning for VLMs

Jun 17, 2026cs.AI

ARIADNE: Agnostic Routing for Inference-time Adapter DyNamic sElection

The increasing deployment of parameter-efficient fine-tuning (PEFT) has led to model ecosystems in which a single backbone is paired with many task-specialized adapters. In this setting, inference-time queries often arrive without task labels, requiring the system to automatically select the most appropriate adapter from a growing and heterogeneous adapter pool. Existing routing methods either depend on access to adapter internals, such as weight decompositions or gradient-based statistics, or require additional router training, which limits scalability and portability as new adapters are added. We introduce ARIADNE, a training-free, adapter-agnostic routing framework for dynamic adapter selection at inference time. ARIADNE represents each adapter through a set of centroids computed from embeddings of its training set, capturing the data distribution associated with that adapter. Given an unlabeled input, it selects an adapter by measuring proximity to these centroids in latent space. Because routing is performed entirely in the input embedding space, ARIADNE is compatible with arbitrary PEFT methods and requires no modification to the adapters or training procedures. Primarily evaluated with Llama 3.2 1B Instruct on 23 diverse NLP tasks, ARIADNE recovers 97.44% of the upper bound performance. Scaling to 44 tasks, it achieves 89.7% average selection accuracy, without additional training or access to adapter internals.

Enrico Cassano, Michał Brzozowski, Zuzanna Dubanowska +2

University of Turin · Samsung AI Center, Warsaw, Poland

Jun 17, 2026cs.LG

RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing

We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, with a public platform available at https://routejudge.cn. Different from model-level response evaluation, RouteJudge focuses on router-level decision quality. For each user query, multiple routing strategies independently recommend candidate models under the same model pool and budget constraints. The selected model responses are then presented to users through anonymous pairwise comparisons, and the resulting user preferences are attributed back to the routing strategies behind the compared responses. Each evaluation record stores the query, routing decisions, model responses, preference labels, cost, latency, and task metadata, enabling preference-aware, cost-aware, and task-conditioned analysis of LLM routers. To support the continuous expansion of routing methods in RouteJudge, we further release ORBIT (Optimal Routing and Budgeted Inference Toolbox), a modular and extensible toolbox that standardizes the end-to-end workflow of LLM routing. ORBIT provides unified interfaces for benchmark loading, query representation, router implementation, budget-aware evaluation, and method comparison, allowing researchers to develop and evaluate routing algorithms under consistent protocols. It also serves as the submission and integration layer for RouteJudge: researchers can implement routing methods within ORBIT, validate them on existing routing benchmarks, and submit compatible routers for online preference-based evaluation. The code of ORBIT is available at https://github.com/LAMDA-Model-Reuse/ORBIT.

Guannan Lai, Haoran Hu, Han-Jia Ye

School of Artificial Intelligence, Nanjing University, China · 2National Key Laboratory for Novel Software Technology, Nanjing University, 210023, China · 3SinapisAI

LLM Evaluation Pairwise Preference Evaluation Cost-Aware Inference LLM Routing

Jun 16, 2026cs.LG

SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs

Sparse Mixture-of-Experts (MoE) architectures enable scaling LLM parameters under a fixed inference budget by activating only a small subset of experts via top-

k

routing. While this preserves causality and suits autoregressive language models, the discrete top-

k

operator is not differentiable, forcing a fixed number of active experts per input and resulting in inefficient use of computation. We propose SoftMoE, which replaces discrete routing with a truncated soft top-

k

LapSum relaxation, allowing gradient-based optimization of expert routing. We further parameterize the mean number of active experts per layer and impose a global budget constraint, enabling the model to learn how to allocate expert capacity across layers. SoftMoE remains fully compatible with autoregressive modeling and achieves performance comparable to or better than sparse MoE on language modeling and downstream tasks, while activating significantly fewer experts. Notably, the learned allocation is highly non-uniform, with later layers activating more experts. The source code is publicly available

^\dagger

.

Mikołaj Zasada, Łukasz Struski, Jacek Tabor +1

AGH University of Krakow, Poland · Faculty of Mathematics and Computer Science, Jagiellonian University, Poland · Jagiellonian University, Poland +1

Mixture-of-Experts Language Models Sparse Mixture-of-Experts LLM Inference Acceleration LLM Routing

Jun 16, 2026cs.AI

FairTutor: Equity-Aware Pedagogical LLM Routing for Budget-Constrained AI Tutoring

Generative AI tutors provide real-time, personalized learning support, but also create a new education inequity: students with access to premium AI services may receive clearer explanations, more personalized guidance, and better scaffolding than students limited to free or low-cost services. To address this challenge, we propose FairTutor, an equity-aware model-routing framework that achieves cost-effective AI tutoring via pedagogically motivated multi-agent orchestration. FairTutor combines query analysis, pedagogical planning, low-cost model generation, evaluator-guided critique and revision, and selective escalation to premium AI models. We introduce access-tier AI Education (AIED) Advantage Gap to measure the quality difference between premium-access and budget-constrained tutoring, and TutorAccessEval, a benchmark spanning math, reading, writing, science, and language learning. Empirical evaluations show that FairTutor achieves 97.1% of premium pedagogical quality (in floor-adjusted Likert scale) while reducing serving cost by 71.6%. Sensitivity analysis reveals a tunable cost--quality Pareto frontier, enabling FairTutor to be tailored to the needs of diverse student populations.

Qingyang Xu

Independent researcher, Shanghai, China

Intelligent Tutoring Systems AI in Education Algorithmic Fairness Cost-Aware Inference Generative AI in Education LLM Routing

Jun 16, 2026cs.AI

DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL

Large Language Models (LLMs) have demonstrated remarkable capabilities in translating natural language to SQL, yet existing methods still falter on complex queries requiring multi-step, data-aware reasoning. We introduce DecoSearch, a training-free framework that addresses this by routing each query to the appropriate level of reasoning effort. A lightweight Schema Selector first prunes the full database schema to the relevant tables and columns. An LLM Judger then decides whether the question requires decomposition: straightforward questions follow a direct generation path and complex ones are escalated to a Directed Acyclic Graph (DAG) of atomic sub-questions, each solved by a targeted SQL generation step. A RAG component grounds the decomposer with semantically similar training examples, and a Topology Refiner restructures the reasoning plan when execution failures signal a flawed decomposition rather than a fixable SQL error. DecoSearch achieves 70.53% execution accuracy on BIRD and 88.31% on Spider with a DeepSeek backbone, surpassing all training-free baselines while consuming an order of magnitude fewer tokens than competing methods. It also functions as a model-agnostic wrapper, consistently improving fine-tuned SQL generation backbones without any modification to the pipeline.

Esteban Schafir, Xu Zheng, Hojat Allah Salehi +4

Florida International University · NEC-Labs · Singapore Management University

Schema Linking Question Decomposition Text-to-SQL LLM Routing

Jun 16, 2026cs.LG

Online LLM Selection via Constrained Bandits with Time-Varying Demand

Large Language Models (LLMs) are increasingly deployed in edge-cloud inference systems to handle diverse user tasks with heterogeneous accuracy, latency, and cost profiles. Selecting the appropriate LLM for each incoming task is critical for ensuring service quality and efficient resource utilization. However, model heterogeneity, stochastic and unknown performance characteristics, and time-varying task demands make static selection strategies inadequate. Real-world deployments often impose hard resource budgets such as monetary expenditure limits, along with soft service-level requirements such as latency guarantees. These constraints introduce additional challenges for online decision-making. We formulate this problem as a constrained stochastic bandit learning task, where the learner sequentially selects models under both packing-type (hard) and covering-type (soft) constraints, while adapting to time-varying task demand. The learner operates without access to the underlying reward, cost, or latency distributions and must rely on partial feedback. We develop a novel online learning algorithm that leverages confidence-bound estimates and demand predictions to balance reward maximization with long-term constraint satisfaction. We provide theoretical guarantees showing sublinear regret and sublinear covering constraint violations compared to an offline benchmark with full information. Experimental results on synthetic workloads demonstrate the effectiveness and robustness of our approach in dynamic, resource-constrained environments.

Yin Huang, Qingsong Liu, Jie Xu

Department of Electrical and Computer Engineering, University of Florida · Manning College of Information and Computer Sciences, University of Massachusetts Amherst

Multi-Armed Bandits Cost-Aware Inference Non-Stationary Bandits LLM Routing

Jun 15, 2026cs.IR

Conversational Query Engine for Mixed-Modality Heterogeneous Enterprise Data Sources

Enterprise business intelligence queries span structured warehouses and unstructured document repositories -- modalities with fundamentally different access methods, cost profiles, and correctness semantics. Existing AI-enabled interfaces force users to select the right tool: NL2SQL systems cannot reason over slide decks, and RAG pipelines lack access to live warehouse tables. We present COGNI, a production conversational BI system that treats natural-language analytics as a heterogeneous query processing problem, organized as four architectural layers. First, an indexing layer implements slide-adaptive chunking -- recursive chunking for plain-text slides, hierarchical chunking for structured content such as tables, charts, and key-value blocks - achieving

88.3\%

on our internal enterprise benchmark. Second, a routing layer built on a LoRA fine-tuned Qwen-2.5-1.5B-Instruct model that produces a dual output - modality decision and complexity assessment at

93.8\%

accuracy and approximately

7\times

lower cost than frontier-model. Third, a retrieval layer executes complexity-adaptive pipelines: a self-correcting NL2SQL agent at

93.9\%

G-Eval, and Recursive Language Models reaching

91.0\%

on multi-hop synthesis queries. Finally, a caching layer validates query equivalence across multiple dimensions beyond embedding similarity, achieving zero false cache hits and

8.4\times

latency reduction.

Darshita Rathore, Vineet Kumar, Vaibhav Singal +2

PayPal Artificial Intelligence Bengaluru, India

Jun 13, 2026cs.AI

ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing

Personalized public transit routing in public transit systems remains challenging due to the difficulty of capturing and integrating diverse user preferences into routing algorithms. This paper presents ChatPlanner, a novel framework that leverages Large Language Models (LLMs) to enable preference aware public transit routing. Our approach employs fine-tuned LLMs with Retrieval-Augmented Generation (RAG) to extract routing parameters and interpret nuanced user preferences from natural language queries, subsequently integrating these preferences into the objective function of a public transit routing algorithm. This study designs preference aware datasets incorporating eight personas and five contexts to establish scoring standards for both fine-tuning and RAG. This work conducted three experiments to validate the solutions' feasibility, extraction of routing information and preferences, and solution set quality and completeness. Results demonstrate that ChatPlanner generates feasible solutions reliably. Fine-tuning enforces the required output structure and learns general preference patterns, while RAG provides query-specific context to resolve imprecise or conversational expressions and calibrate continuous scores. The combination of both achieves the highest accuracy in routing information extraction and user preference interpretation. Results based on selected case studies show that by capturing user preferences, ChatPlanner identifies valuable solutions across different dimensions that existing route planners overlook, generating more valuable route alternatives. This research establishes a new paradigm for integrating natural language understanding into transportation optimization.

Tingting Yang, Chenhao Xue, Jun Chen

School of Engineering and Materials Science, Queen Mary University of London Mile End Road, London, E1 4NS, United Kingdom · Department of Engineering Science, University of Oxford Parks Road, Oxford, OX1 3PJ, United Kingdom

Intelligent Transportation Systems LLM Routing User Preference Modeling

Jun 13, 2026cs.AI

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 Attacks on VLMs Multimodal Robustness Adversarial Perturbations LLM Routing Multimodal Foundation Models

Jun 12, 2026cs.LG

When to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge Editing

Knowledge editing systems must update selected facts while preserving nearby but irrelevant behavior. This paper studies this problem in a memory-assisted setting where an edit memory is retrieved at inference time and a parameter-efficient adapter corrects the model's object preference. We argue that the central design question is not only how to write an edit, but also when to suppress it. We introduce RRDA, a route-specialized dual-adapter editor. A relevance router first decides whether a prompt should receive an edit memory. Routed prompts use an edit adapter trained to prefer the new object over the original object; unrouted non-direct prompts use a separate locality adapter trained to preserve or restore the original-object preference. We evaluate RRDA on three 1,000-case protocols, CounterFact, ZsRE, and MQuAKE-CF, under the same memory protocol and two 7B/8B base models. On Llama-3.1-8B-Instruct, RRDA obtains the best overall probability-preference accuracy on all three benchmarks: 0.8180 on CounterFact, 0.8946 on ZsRE, and 0.9922 on MQuAKE-CF. The same trend holds on Qwen3-8B. Router ablations show that the relevant memory boundary differs across datasets: a lexical neural router is safest on CounterFact, while BGE embedding routing is better on ZsRE and MQuAKE-CF. Memory, component, and module ablations show that explicit memory supplies the largest edit gain, while route-specialized adapters improve the final reliability-locality balance rather than simply increasing LoRA capacity.

Baijia Zhang, Yining Huang

Xinjiang University · Meta Emergence Laboratory

Knowledge Editing Factual Knowledge in Language Models LLM Routing Model Editing

Jun 12, 2026cs.LG

A theoretical model for task routing in mixture-of-expert transformers

Mixture-of-experts (MoE) layers enable the scaling of transformer models while keeping the inference compute fixed. While task-expert specialization has been observed in empirical studies of frontier MoE transformer models, existing theoretical work analyzes this using continuous mixture models that cannot be used to model natural language effectively. An important open question is to \textit{theoretically explain task-expert specialization in transformer MoE models using discrete models of language}. To address this, we represent structured knowledge via syntactic templates and finite key-value dictionaries, and prove formally that a single-layer MoE transformer can encode knowledge by using experts that specialize in the corresponding tasks. Our construction shows how queries are routed to unique, task-specific experts whose size depends solely on the intrinsic complexity of the given task (i.e. the combined size of its syntactic templates and factual dictionary). Our construction provides a theoretical support for empirical results on localized knowledge circuits in MoE models. We support our theoretical findings with experiments evaluating model performance under varying MoE loss functions.

Vinoth Nandakumar, Yongli Xiang, Yunzhi Yao +2

University of Sydney · Zhejiang University · Google Research

Transformer Expressivity Mixture of Experts LLM Routing Mixture-of-Experts Models

Jun 12, 2026cs.LG

Cost-Optimal LLM Routing with Limited User Feedback under User Satisfaction Guarantees

Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expect high-quality responses, and in commercial settings this is formally codified in Service Level Agreements (SLAs), creating a fundamental tension between cost and quality. Recent progress on cost-aware LLM request routing has shown potential to resolve this tension, but existing approaches rely on complete feedback signals, offline training, extensive per-workload tuning, and most lack SLA guarantees or inference-time adaptivity. We introduce SLARouter, an online routing algorithm that learns a cost-optimal policy from the sparse, one-sided user feedback available in production systems. SLARouter provides theoretical guarantees for both cost optimality and strict SLA compliance. Experiments across a wide range of LLM benchmarks show that SLARouter satisfies SLA constraints without the need for per-benchmark tuning, reducing operating cost by up to 2.2x over existing baselines.

Herbert Woisetschläger, Arastun Mammadli, Ryan Zhang +1

Technical University of Munich Germany · University of Exeter United Kingdom · Horace Greeley High School United States

Cost-Aware Inference LLM Routing

Jun 11, 2026cs.DC

STREAM: Multi-Tier LLM Inference Middleware with Dual-Channel HPC Token Streaming

Researchers and practitioners working with large language models face a fragmented landscape: local models are free and private but hardware limits the model size and context windows a researcher can use; institutional HPC centers offer powerful GPU resources at no marginal cost and keep data within institutional boundaries, but operate behind firewalls and are designed for batch jobs rather than interactive use; commercial cloud APIs provide frontier-model quality on demand but impose significant cost and data retention policies unsuitable for sensitive research data. No existing system unifies all three. STREAM (Smart Tiered Routing Engine for AI Models) addresses this gap with four contributions: (1) a three-tier routing architecture combining local, HPC, and cloud inference with a local LLM-based complexity judge; (2) a dual-channel HPC streaming architecture that separates the Globus Compute control plane (authentication and job dispatch) from a WebSocket relay data plane (token delivery), enabling sub-second TTFT (0.54 s median, 21.1x over batch mode's 11.40 s) through institutional firewalls without VPN or firewall rule changes, with end-to-end AES-256-GCM encryption ensuring the relay operator cannot read token payloads; (3) tier-aware context summarization that prevents long conversations from forcing simple queries onto expensive tiers; and (4) an HPC-as-API proxy mode that exposes HPC inference as an OpenAI-compatible endpoint callable from any standard client with no HPC expertise, a deployment pattern made practical only by the sub-second TTFT of contribution (2). Llama 3.2 3B achieves 85.1% free-tier retention on a 1,200-query benchmark spanning ten domains. Measured TTFT: 0.26 s local, 0.54 s HPC (relay), 1.68 s cloud.

Anas Nassar, Steve Mohr, Leonard Apanasevich +1

Advanced Cyberinfrastructure for Education and Research (ACER) University of Illinois Chicago Chicago, Illinois, USA

LLM Serving LLM Inference High-Performance Computing LLM Routing

Jun 11, 2026cs.AI

Brick: Spatial Capability Routing for the Mixture-of-Models (MoM) Paradigm

Defining query difficulty is one of the hardest problems in deployment engineering. Existing LLM routers rely on surface features such as domain labels, keywords, and token count, ignoring the within-domain variance that actually determines model success. Frontier models cost ten to one hundred times more than local open-weight models, so at production scale even small per-request savings become a direct cloud-bill lever. We present Brick, a multimodal router that scores each model on six capability dimensions, combines this with a per-query difficulty estimate, and dispatches via a cost-penalized geometric rule. A continuous preference knob lets operators slide between max-quality and max-saving profiles at deploy time. On a benchmark of 5,504 queries, Brick at max-quality reaches 76.98% accuracy, beating the best single model (75.02%) and all tested routers. At a neutral cost-quality profile, Brick achieves 74.11% accuracy at 4.71x lower cost than always using the strongest model. At min-cost, it cuts cost 22.15x with 11.85 points accuracy loss. Median latency drops from 51.2s to 22.8s.

Francesco Massa, Marco Cristofanilli

Adaptive Model Routing Cost-Aware Inference LLM Routing

Jun 11, 2026cs.AI

ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning

Multi-agent debate (MAD) can improve large language model reasoning, but fixed debate pipelines often waste computation and can amplify correlated errors among similar agents. We propose ARMOR-MAD, a training-free heterogeneous MAD framework that treats debate as conditional computation. ARMOR-MAD combines three components: Pre-debate Agreement Routing (PAR) decides whether independently generated Round-0 answers require debate; Early Agreement Stopping Evaluator (EASE) stops debate after convergence; and Semantic Outlier Detection (SOD) down-weights abnormal final answers during aggregation. Across MATH Level 5, GSM8K, MMLU, and MMLU-Pro, ARMOR-MAD consistently improves over fixed-round heterogeneous debate with the same model pool, reaching 65.5%, 96.5%, 90.0%, and 81.5% accuracy, respectively. The results suggest that genuine model heterogeneity and agreement-based control are both important for making MAD more accurate and efficient.

Fuqiang Niu, Bowen Zhang

School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China · School of Artificial Intelligence, Shenzhen Technology University, Shenzhen, China

Multi-Agent Debate Multi-Agent Consensus LLM Routing Multi-Agent Reasoning

Jun 11, 2026cs.LG

When Does Routing Become Interpretable? Causal Probes on Block Attention Residuals

Block Attention Residuals (Block AttnRes) by replace fixed additive residuals with a learned softmax over earlier depth-source representations, surfacing cross-layer routing as an inspectable tensor in the forward pass. This is a tempting interpretability target: information flow normally inferred indirectly is now directly observable. We ask whether such exposure suffices for mechanistic interpretation. We probe two same-scale (

0.6

B) Block AttnRes checkpoints under identical routing-ablation interventions: a vanilla Qwen3 inference-wrapped through a deterministic recency-bias schedule that the codebase admits as a routing-equivalent loading path, and a Block AttnRes Qwen3 trained from scratch with routing as part of optimisation. The wrapped baseline's routing weights are content-independent and reproduce the schedule's analytic prediction. The trained AttnRes checkpoint instead exhibits three localised routing motifs: an embedding-source pathway through early-layer MLP, a current-state pathway through early-layer attention and MLP, and an older-history pathway through late-layer attention. Beyond this stratification, we find a sharp dissociation between average routing mass and causal importance: in both sublayers, the largest mass slice is not the largest causal contribution, and one source family carries appreciable mass with no detectable causal role under intervention. Architectural exposure of routing is therefore necessary but not sufficient for mechanistic interpretation: structured depth routing emerges only when routing has been part of training, and even then, descriptive routing summaries should be treated as candidate hypotheses to be tested by causal interventions, not as evidence of mechanism in their own right.

Aydin Javadov

ETH Zurich

Transformer Interpretability Attention Residual Connections Mechanistic Interpretability LLM Routing Causal Interpretability