Jonathan B. Martin, Yashwant Kurmi, Charlotte R. Sappoeess.IV cs.CV
Ultra-low-field MRI makes neonatal brain imaging deploy- able in low-resource settings, but its low SNR, lack of shielding, and long scan duration make it especially prone to acquisition artifacts, motivating automated quality control. We address the LISA 2026 Task 1a challenge: multi-label severity grading (0/1/2) of seven common image artifacts on ULF T2 weighted volumes. We identify that a number of backbones may be successfully paired with a classification MLP, but that no single backbone is uniformly best across artifacts. To improve performance, we evaluate routing complementary foundation model teachers through a per-artifact gate, as well as distilling the teachers into a single in-domain ViT-S student (LoFi RADIO) over an unlabeled low-field MRI corpus. Both of these strategies improve the weighted composite. The distilled backbone matches or exceeds the gate and has the added advantage of not requiring deployment of multiple large foundation models at infer- ence.
The remarkable performance of multimodal large language models (MLLMs) comes at the cost of substantial computational overhead, posing significant challenges to real-time deployment and cost effectiveness. Existing model routing approaches either decide from coarse request-level features alone or spend one or several extra language model passes to inspect the generated response, leaving the token-level uncertainty signals that emerge during generation unused. To address these limitations, we propose Pro-Router, a token-aware progressive model routing method with adaptive edge-cloud collaboration for efficient multimodal LLM inference. Pro-Router employs a two-stage progressive decision mechanism. First, a lightweight prompt pre-scorer module performs rapid pre-screening before token generation begins, guiding apparently simple requests to small models. Second, a token-aware verifier reads the sampling probability distribution of each token the small model generates, estimating the model's confidence in its own output to determine, per request, whether the answer ships or escalates to the cloud-based high-precision model. Furthermore, we design an adaptive edge-cloud serving pipeline that sizes every dispatch to each device's measured service rate, so both the edge and the cloud tiers stay fully utilized without manual parameter tuning and are not impacted by the network latency. Extensive experiments on multiple multimodal benchmark datasets and models demonstrate the effectiveness of Pro-Router. Compared to other methods, it achieves the highest routing accuracy and improves routing speed by more than 10x. Its serving pipeline also reaches more than 75% higher end-to-end throughput than the existing model routing pipeline. Our code is available at https://github.com/xinyuangui2/pro-router.
Agents with smaller language-model backbones are less expensive but can drift into persistent failure modes, whereas those with larger backbones are generally more reliable but more costly. This reliability-cost trade-off motivates routing methods that decide when to invoke an agent with a larger backbone: before execution, after a fixed trajectory prefix, or locally at individual steps. Our method, TACIT-SWITCH, learns permanent handoff policies from accumulated trajectory evidence and Teacher-Annotated Censored Intervention Times (TACIT). It represents each annotation as an interval-censored observation on a cumulative-risk scale. The resulting mixture-cure threshold model estimates the probability that the paired Strong rollout succeeds and, conditional on success, the handoff threshold; no teacher is required at deployment. In a mechanism-based multi-step simulation, TACIT-SWITCH improves success by 7.4-11.1 percentage points over task-level, step-level, and fixed-prefix routing baselines at comparable cost. Within that controlled simulation, ablations show that task features and cumulative trajectory risk provide complementary information. With operating points selected on development data, TACIT-SWITCH achieves the highest held-out success among learned policies on both ALFWorld (48.5% with 4B Cheap; 45.5% with 9B Cheap) and DABench (73.1%).
An LLM router picks which model should answer each query. The appeal is that models fail on different questions. Whatever single model is best overall still gets some wrong, and another model in the pool gets many of those right. Getting that choice right every time is the ceiling, and a router is an attempt to approach it. However, recent work reports that routers do not get close. Across 21 routing methods on five benchmarks, sharply different designs land within a fraction of a point of each other, and all of them stay far below that ceiling. Learned routers often fail to beat simply always calling the strongest model. We ask what those missed questions have in common. We set fourteen models to answer all 294 questions, with 7 task types across 3 languages: Korean, English and Hindi. We ran the whole matrix twice, changing nothing, but 5.37% of the 4,116 model-question pairs came out scored differently anyway. Run-to-run movement like that is normal, and we argue that a small win does not show that routing did anything, ours or anyone else's. Counting an answer correct only when the model got it right in both runs, 29 questions on this matrix can be improved with routing. Every correct-answer count here is on that rule. Task type accounts for most of them: assigning each task type one model in advance, chosen once and never updated, improves 21 of the 29. Splitting each task type by language improves 2 more and leaves 6 of 294 unoptimized. That handful is what a learned router would have been built for, and it is smaller than the run-to-run movement above, which is a share of pairs rather than of questions. The static table we adopted answers 262 of 294 questions at $3.33 per run, against the best single model's 245 at $7.69. All of this is fitted and scored on the same 294 questions with no holdout.
Adam Fisch, Shubhendu Trivedi, Fantine Huot +5cs.AI
Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the specialist who can answer most effectively at the lowest cost. Routing requires estimating each specialist's expected return, but this value estimation has a cost. Cheap estimators (e.g., embedding-based predictors) are fast but noisy, while accurate estimators (e.g., fine-tuned models with access to retrieval results or partial reasoning traces) are expensive. We formalize this tradeoff as an instance of Pandora's Box, the classical problem of optimal search with costly inspection. Under a Gaussian signal model, the resulting policies have closed-form value-of-information expressions that determine, for each specialist and input, whether refining the value estimate is worth its cost. We call the centralized policy Pandora's Router. We extend this to a decentralized setting, Pandora's Bidder, where specialists independently decide whether to invest in self-assessment before accepting an offered price to claim a query. Experiments across three domains---a standard multi-LLM benchmark, retrieval-augmented specialists, and LLMs with variable inference-time reasoning---show that Pandora's Router matches the routing quality of exhaustive estimation, while querying the expensive estimator far less often. In the decentralized setting, value-of-information reasoning improves allocative efficiency when competing estimates are accurate; when competing estimates are noisy, however, it can increase the strategic specialist's utility at the expense of others.
As large language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the ecosystem. Auditing the quality of their inference APIs is therefore an open problem. We formalize hosted model routing as a stochastic process and propose \mbox{\textbf{Ventor-QTest}}, a composite black-box audit that requires no probability information from the target API. Its repeated-request component sends each frozen constrained context to the target multiple times, reconstructs a categorical output distribution from the returned text counts, and reports \emph{average fidelity loss} (AFL) as a null-bias-corrected, within-window mean coarsened-KL statistic. Its long-sequence component uses independent runs to report \emph{extreme fidelity loss} (EFL) through the empirical upper tail of a run-level reference-centered-surprisal statistic. Across three logprob-capable route conditions, AFL shows strong linear descriptive agreement with a logprob-derived coarsened-KL comparator. Across seven route snapshots, 20-run sequence probes reveal route-specific EFL variation. AFL and EFL have little detectable route-level association with GPQA-Diamond accuracy. In contrast, pronounced EFL coincides with a decline in Terminal-Bench pass rate as task exposure increases. This pattern may arise because correctness in long-horizon tasks is more sensitive to extreme fidelity loss. These results motivate reporting AFL and EFL jointly, particularly when auditing long-horizon agentic tasks. The open-source implementation is available at https://github.com/Tencent/AI-Infra-Guard/tree/main/services/api_checker/ventor_qtest.
Model routing aims to select the most suitable model from a candidate pool for each query, balancing quality and cost. Existing VLM routing research is limited to traditional VQA evaluation, lacks systematic calibration optimization for open-set scenarios, and employs training objectives that dilute multi-positive signals via softmax normalization without incorporating cost. We address these limitations with three contributions: (1)VLM-ExecRouterBench, the first execution-oriented VLM routing benchmark covering Code, Agentic, and Search domains with 11 candidate models spanning nearly two orders of magnitude in pricing; (2)SCOPE-Router, a dual-tower router that matches queries to model behavior profiles constructed via hybrid calibration (random/diagnostic/diversity sampling), enabling new models to join routing without retraining; (3)CRM+RCCR, an architecture-agnostic cost-aware objective that encodes cost preference into continuous relevance targets through per-pair independent scoring, eliminating multi-positive dilution while regularizing queries with similar routing preferences to be closer in the routing space. Empirically, SCOPE-Router achieves the best Rank Score on all three benchmarks, surpassing the runner-up by 1.84 points under OOD settings and by 6.75 points under doubly OOD open-set evaluation. When applied to four diverse routers, CRM+RCCR improves Rank Score by 1.25--6.21 points.
LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as formatting or tool-argument construction. Prior routing methods exploit this asymmetry by assigning easy invocations to a cheaper small model and difficult ones to a large model. Such policies reduce inference cost, but they leave the small model's capability unchanged, so attainable savings remain bounded by the work the student can already solve. MERA instead improves the small model itself, using a single model invocation as the unit of adaptation. In each cycle, MERA replays failed student invocations to obtain execution-verified teacher demonstrations, distills recurring procedures into an iteratively updated SkillBook, and fine-tunes a student LoRA adapter via supervised learning and optional GRPO. Routing serves as supporting machinery for deployment: the improved student is served behind a cost-calibrated router with verifier-backed fallback, and a candidate SkillBook, adapter, or router is admitted only when joint replay preserves task quality. Empirically, four-cycle adaptation raises Qwen2.5-Coder-1.5B from 28.7% to 49.7% pass on held-out HumanEval+MBPP. Under verifier-backed fallback, the deployed policy retains 88.3% pass at 60.8% of always-Luna cost. On TAU-2, a fine-tuned Qwen3.5-2B improves from 14/35 to 18/35 and matches an unadapted 4B model. These results indicate that verifier-backed multi-cycle adaptation can increase small-model capability, rather than only routing around a fixed student.
Srinivasan Manoharan, Junhua Zhao, Fangbo Tu +6cs.LG
Enterprise AI coding assistants incur substantial inference spend, and naive token-cost minimization often fails to reduce end-to-end cost once retries, escalations, and developer wait time are included. We present Task-to-Model Optimization (T2MO), a data-driven methodology for optimizing model selection in production coding workflows. We treat each developer session as a task that can be discovered, classified, graded for difficulty, benchmarked in a production-like harness, and routed to the cheapest model able to complete it within quality and latency constraints. The framework is a nine-stage pipeline spanning telemetry instrumentation, taxonomy discovery, difficulty grading, benchmark construction, candidate evaluation, optimal mix derivation, forecasting and version planning, staged routing deployment, and continuous governance. Unlike token-centric routing rules, our objective is cost per completed task, with failure escalation priced in explicitly. We show that this expected-completion-cost objective weakly dominates token-cost minimization under escalation, and we derive the routing boundary, the minimum pass rate a cheaper model must reach on a given cell to be worth deploying. Decisions are organized as a two-level hierarchy of task category difficulty tier, and per-cell displacement opportunities are aggregated into a traffic-weighted savings waterfall that ranks replacement candidates by realized dollar impact. The framework supports developer guidance, spend forecasting, and a staged transition from static policies to shadow-mode classifiers, verified cascades, and ultimately an intelligent router. We describe the methodology, optimization objective, evaluation protocol, and governance loop in a form suitable for production deployment and future empirical study.
LLM routers promise efficiency by matching each request to the cheapest adequate model, and are increasingly applied per step inside multi-step agents. Yet agentic routers are evaluated like single-turn routers: by replaying logged trajectories and substituting another model's recorded outputs, assuming the rest of the trajectory is unaffected. We test this assumption with branching rollouts: we fork live SWE-bench agent trajectories at controlled points, rebuild the environment, continue each fork with a different model, and compare against same-model control forks that isolate sampling and replay noise. Across six paired runs (~900 rollouts), swaps exceed their matched control floors by +0.25 to +0.66 normalized edit distance (multiplicity-corrected CIs exclude zero), rewriting 61-94% of post-fork actions; 74-77% of early swaps diverge at the first post-fork action, versus 6-35% of controls, leaving only 3% of replayed states valid. Divergence decreases with fork depth in both directions. All five outcome flips we observe occur in swap arms, upgrades rescuing unsolved instances and a downgrade losing the sole solve, and zero occur across 359 control forks. Scoring these same swaps with a log-stitching replay evaluator, replay mispredicts every success-relevant outcome call and predicts patches with 0.00-0.11 similarity to reality. Auditing the noise floor, temperature-0 "determinism" is configuration-dependent: FP8-served controls diverge on over 90% of forks while AWQ-served ones remain near-identical; and under tight budgets the stronger model more often exhausts its steps without submitting. Replay-based benchmarks score the wrong world for agentic routing; we release our harness and all trajectories.
No single large language model (LLM) is optimal across all queries and budget constraints, making model routing essential for cost-effective deployment. Existing routers adopt diverse formulations and implementations, making fair comparison and extension difficult. We present a unified formulation of LLM routing as a sequential decision process characterized by five components: context encoders, model encoders, scoring functions, decision rules, and learning signals, covering single-turn, multi-turn, and personalized routing. Based on this formulation, we develop an automated pipeline for constructing routing supervision and evaluating routers jointly on response quality and inference cost. The resulting benchmark, xRouteBench, spans generic LLM, memory-augmented, vision, time-series, and personalized routing tasks. We further introduce LLMRouter, an open-source modular infrastructure with more than 16 representative routers. Our empirical study shows that learned routers outperform the strongest fixed-model baseline by 14.6% relatively, lightweight routers become more competitive under tight cost constraints, and user-conditioned routing consistently improves personalization.
Most document-extraction systems use a single model for all documents. This is simple but can be costly for easy cases and less effective for difficult ones. We examine whether we can predict a document's difficulty before extraction using inexpensive, document-based signals, and use this to choose between a cheaper and a stronger extractor. We find that routing only helps if two conditions hold: the cheaper model fails often enough to make routing worthwhile, and those failures can be predicted from visible features such as image quality and layout. We turn these into a practical test and apply it to five genres. When both conditions are met, the calibrated router reduces cost by 31-33% on receipts and 77% on degraded ad-buy forms while keeping quality within 0.02 F1 of always choosing the large model. Routing does not help if either condition is missing, as with clean digital invoices or nutrition labels that are already easy to read. A small labeled pilot can predict whether routing will work, and in the two cases where we ran it first, the prediction was correct. A simple bag-of-words router works about as well as engineered features, showing that the main limit is the genre, not the router design; we use interpretable features to help explain which genres can be routed. The router must be retrained for each dataset and does not transfer across datasets, even within the same genre. These results hold for two model pairs with cost differences of 5x and 3x.
Jingzhi Gong, Jie M. Zhang, Gunel Jahangirova +3cs.SE cs.AI
Code generation systems make each LLM call with a model, a prompt, and decoding settings. However, existing optimization methods usually tune only part of these choices or use one fixed configuration for all tasks: global optimizers search one configuration for all tasks, routers choose only a model, and prompt optimizers keep the model and decoding settings fixed. This leaves their joint, group-specific interactions unclear. We therefore examine how these choices interact and observe that prompts and decoding settings interact, tuning effects vary by model, and the best configuration varies by task difficulty. Guided by these observations, we introduce COMPAS (Code-generation Optimization over Models, Prompts, And Decoding Settings), a difficulty-aware method that learns group-specific quality-cost fronts through low-cost model selection and joint prompt-decoding search, then routes each test task to its matching front online without further search. Under a matched search budget on LiveCodeBench, COMPAS improves pass@1 from 45.9% for the best baseline to 52.8% while reducing cost from $36.57 to $4.92. This also transfers to repository-level code generation on SWE-bench, resolving 76.0% of tasks versus 70.0% for the best baseline. Code and the reproducibility artifact are available at https://github.com/gjz78910/COMPAS.
Production deployments often swap between different-sized models in a family for cost-quality cascading, mid-conversation switching, and routing, and each swap forces the receiver to repay the prefill from scratch. We propose cross-model KV cache transfer, where the receiver reuses the source's KV cache, skipping prefill. We find that cross-model KV has substantial linear structure across matched-KV pairs, where source and target share KV head count and per-head dimension. On Qwen3 14B->32B, one source layer explains 56% of variance in the target's keys and 32% in values, rising to 79% and 65% with multiple source layers. Building on this, we design a closed-form ridge mapper that operates per head and proceeds in three steps. First, for each target layer we select the top-k most predictive source layers and concatenate their KV as input. Second, we strip RoPE from the keys before mapping, so the fit is position-free and reusable across context lengths. Third, we fit ridge regression on a small calibration set of 500 FineWeb-Edu sequences of 1,024 tokens each. Surprisingly, across six pairs in three families, this linear mapper retains 73-98% of the receiver's standalone-prefill accuracy on four pairs, while two degrade sharply. A nonlinear MLP recovers up to +37 pp HellaSwag retention on the failures. The mapper runs 2.7-25x faster than re-prefill and remains stable across multi-turn handoff, making cross-model KV cache transfer practical.
Agentic systems have widened the gap between producing candidate outputs and reviewing them. This paper asks a practical architectural question: should domain specialization be built into an evaluator's weights, or into the rule that decides when its judgment can be trusted? We study 99,952 public, rubric-conditioned examples. Supplying the correct rubric improves locked-test accuracy by 2.11 points over a response-only control; replacing it with an unrelated rubric costs 2.66 points. Dividing the same training corpus among eight criterion-family LoRA judges, however, loses 10.05 points and cuts audited coverage at a 5% risk target from 24.44% to 5.43%. Matching the bank's stored capacity with one rank-64 adapter does not reproduce this loss. Nor is the result explained by learning rate or optimizer steps. Initializing the family adapters from a shared, trained judge recovers test accuracy to 76.85%, 19.94 points above scratch training at the same learning rate (95% interval 18.88-21.02). The result changes when specialization governs deferral rather than judgment. On RewardBench 2, learned correctness heads route examples through a 0.6B-4B-8B cascade without changing any reward score. Across 20 locked repartitions, the cascade attains 89.40% accuracy, compared with 84.75% for 8B alone, at 0.415 normalized parameter compute. Every run passes an exact one-sided 95% risk audit; margin-based rules remain near 84.8% accuracy while using at least 0.94 compute. These results suggest a qualified design rule: share the learning of judgment until there is enough data to justify a split, and place domain-specific adaptation in an audited release boundary.
Agentic systems increasingly delegate model selection to a router, yet open-source routers are usually evaluated with different tasks, candidate pools, and execution protocols, limiting direct comparison. We present a common measurement protocol and hybrid evaluation of four router implementations across RouterBench, BFCL v4, tau2-bench, and WebArena. We evaluate 290 frozen tasks against a locked matrix of 2,610 candidate outcomes. Three routers emit constant or near-constant tier assignments; only vLLM Semantic Router varies materially with prompt content, and it has the highest observed success rate on none of the four benchmarks. Always-Mid matches Aurelio exactly on three benchmarks and within 0.003 on the fourth. For vLLM, task-level superiority tests detect no task-specific advantage over a share-matched content-blind allocation; equivalence is established only on WebArena at the protocol-declared five-percentage-point margin. The results show that, under these configurations and controls, observed gains track selected-tier composition more closely than demonstrated task-specific targeting. Fixed-tier baselines and selected-tier distributions are therefore necessary controls in router evaluation; the findings are scoped to these configurations, candidate pool, and frozen benchmark samples, not to routing paradigms in general.
Biomedical image analysis spans diverse modalities and tasks, yet real-world deployment is hindered by severe distribution shifts across scanners, protocols, and patient populations. High-performing models consequently require repeated domain-specific fine-tuning, which is a costly cycle that becomes impractical when labels are scarce or privacy constraints limit data sharing. We propose OPERA (Offline Policy-guided Expert Routing and Adaptation), a multi-agent ensemble framework that addresses this deployment bottleneck by treating expert weight assignment as an offline policy learning problem: a routing policy is learned from a small validation set without gradient updates to any expert agent, then deployed with test-time adaptation to handle distribution shift. OPERA coordinates heterogeneous specialist agents through complementary mechanisms. The expert profiling module learns selection policies offline, enabling informed allocation of expertise. Each agent undergoes confidence calibration through temperature adjustment, ensuring more reliable probabilistic outputs. OPERA also incorporates distribution aware adaptation, where class weights are dynamically adjusted at the batch level using statistics derived from unlabeled test data. Instance level routing assigns each sample to the most suitable expert by leveraging inter model agreement and predictive entropy. We evaluate OPERA on 9 datasets covering fundus photography, chest X-ray, CT, MRI, and multimodal diagnostic benchmarks, comparing against 30+ baselines across classification, segmentation, and multimodal settings. OPERA consistently improves performance and calibration quality, demonstrating that offline policy-guided expert agents coordination is a practical path to deployable biomedical AI without retraining. Code is on \href{https://github.com/HUANGLIZI/OPERA}{GitHub}.
We present DS@GT's submission to FinMMEval 2026 Task 1, a multilingual financial exam question answering benchmark spanning English, Spanish, Greek, Chinese, and Hindi. Financial certification exams such as the CFA, EFPA, and CPA demand structured domain reasoning that standard NLP benchmarks do not capture, and this challenge compounds across languages where retrieval and representation infrastructure is underdeveloped. We build a retrieval-augmented pipeline on LangGraph that detects query language and retrieves semantically relevant exemplars from a 30,209-entry multilingual knowledge base using BGE-M3 embeddings and FAISS indexing. The system then scores answers via Retrieval-Augmented Direct Scoring (RADS), reading next-token log-probabilities over candidate option letters rather than generating free-form output. For low-resource languages, we fuse per-language and cross-lingual retrieval indices using weighted Reciprocal Rank Fusion. Model selection is language-routed: Qwen3-14B for Arabic, Chinese, and Hindi; Qwen2.5-14B for English; and Llama-3.1-8B for Greek, a routing derived from empirical ablations that reveal substantial language-asymmetric performance gaps. Notably, chain-of-thought prompting significantly degrades Greek accuracy (90.7% to 20.9%), and enabling Qwen3's default thinking mode collapses Arabic RADS performance to near-chance levels. Our results indicate that effective multilingual financial reasoning requires language-aware retrieval, model routing, and deliberate scoring strategy selection.
Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect answer. Existing cost-aware systems typically treat such failures as cascade decisions: try a cheap model first, then escalate hard cases to a stronger and more expensive model. In coding, however, execution feedback can also make further cheap-model recovery worthwhile, raising a budgeted deployment question: when should an agent spend more cheap compute, and when should it escalate? We formulate this post-failure decision as recovery routing over heterogeneous actions and train a supervised router from execution rollouts. To make the same router usable under changing budgets, we add a Conformal Risk Control (CRC) layer that selects a deployment-time cost penalty without retraining and provides marginal expected-cost control under exchangeability. Across held-out failures from five coding benchmarks, cheap recovery and escalation exhibit complementary success patterns. The calibrated frontier improves over fixed actions, prompt-only routers, and a binary cascade baseline; in the main GPT-5.4-nano/GPT-5.4 setting, one CRC-calibrated frontier point exceeds always-escalate solve rate while using 35% of its mean recovery cost. Code is available at https://github.com/Qijia-He/agent-budget-control.
Large language models are increasingly deployed as agents, but reliable agentic behavior requires more than next-token prediction. At inference time, it is preferred that an agent can decide whether to proceed with its current reasoning, defer to a stronger model, request additional information, invoke external tools, or abstain under the given setup. Existing approaches address these decisions through prompt-level routing, external orchestration, or task-specific fine-tuning, which primarily rely on input-side signals, and are often costly and difficult to maintain as model backbones evolve. We ask whether such control decisions can be inferred directly from a model's latent generation process. We introduce Multi-Head Latent Control, a lightweight layer that reads hidden-state trajectories from a frozen LLM or VLM to produce deployment-time control signals. A Capability Head predicts whether the current model can solve the instance or should defer to a stronger collaborator, while a Resolution Head predicts appropriate resolution decision Clarification, Tool Use, Abstention, or Direct Answering. Both heads are trained only on latent traces from the same frozen LLM backbone, enabling post hoc adaptation without modifying the model. Across language and vision-language settings, Multi-Head Latent Control consistently improves the quality-cost tradeoff of multi-model systems, enabling early handoff from partial generations and more accurate intervention decisions. In routed execution (small + large model), it reduces large-model usage by up to 90.7 percent on AndroidWorld and 27-53 percent on average across benchmarks, while retaining most of large-model performance. Additionally, the learned control signals improve tool-use decision quality, yielding up to +158 percent relative score gain and 65.5 percent fewer missed-required tool calls.
Xinchen Liu, Hang Zhou, Yingjie Zong +12cs.CL cs.AI
Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verification. At the same time, frontier and open models are becoming structurally specialized: a model that is strong at code editing, long-context recovery, tool use, mathematical reasoning, or low-latency response may not dominate on the other axes. This makes model selection inside an agent a core systems problem rather than a per-query serving trick. Existing routing methods mostly optimize single-turn cost-quality trade-offs and therefore miss the execution state, intermediate failures, and feedback loops that make agents different from chat completion. We propose Harness-Native agentic routing, a step-level routing paradigm that selects either a single best-fit model for cost-effective execution or multiple complementary models for ensemble-style accuracy improvement, conditioned on the full harness state. The key insight is that every routing decision naturally produces a structured data record -- consisting of the query, harness state, model choice or model set, execution trace, outcome, and cost -- whose labels are supplied by the environment rather than by the router itself. These records form a harness-native data flywheel: execution traces train better routers and harness-native models, which improve cost-quality trade-offs and generate more traces under the same budget. We instantiate this idea in OpenSquilla with a four-layer routing stack, an open LightGBM cold-start ranker, and a staged router-model path that turns logged arena records into progressively stronger routing policies. The report studies singleton and multi-model routing on agentic benchmarks including DRACO and PinchBench, and argues that agentic routing is not merely cost control, but a data engine for agent-native training.
Can AI agents visually comprehend quantum circuit diagrams and generate verified executable code--and at what cost? We present Quantum Circuit Vision, a cost-aware evaluation framework for multimodal AI agents on quantum circuit visual understanding. We construct a 132-circuit benchmark spanning 13 categories ($1$--$10$ qubits) with executable Amazon Braket code and unitary-fidelity verification. Evaluating three frontier Claude-family models at different capability-cost tiers with $n=5$ repeated trials, we find that the mid-tier model (Sonnet 4.6, $1.30\times$ credits) offers the most favorable balance on the cost-accuracy frontier: 91% pass rate on the core subset at 18% of the per-call cost of the strongest model (Opus 4.6), whose accuracy advantage is not statistically significant (paired $t$: $p=0.083$). Logistic regression confirms that circuit depth--not qubit count--is the primary predictor of failure ($p<0.001$). Chain-of-thought prompting shows no statistically significant effect (all $p>0.18$, $n=5$), suggesting that visual pattern recognition outweighs explicit reasoning strategy for structurally coupled diagrams. We propose a cascade routing strategy (cheap $\rightarrow$ expensive models) that achieves 84% accuracy at 38% of single-model cost, demonstrating that model routing dominates prompt engineering as a cost lever. We release QCV-Dataset (132 circuits, 5 modalities, 1,931 files) on Hugging Face Hub as an open evaluation infrastructure with structured metadata for discoverability, interoperability, and responsible AI documentation, and all evaluation code, cost logs, and verification scripts on GitHub for full reproducibility.
Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. However, existing frameworks typically call APIs, based on coarse-grained matching between tasks and the functions of expert models or tools, while overlooking critical factors such as performance variability and cost efficiency among functionally similar alternatives. To address this, we propose Agora, a framework that uses a confidence-calibrated auction to dynamically allocate tasks to expert models and tools. By treating reasoning steps as tradeable items, Agora bases allocation on calibrated competence rather than raw confidence. Across five main benchmarks, Agora improves or remains competitive with single-model, routing, and cascade baselines under matched candidate pools.
Routing among large language models (LLMs) trades response quality against serving cost, motivated by the reported gap between deployed routers and a per-instance oracle. Recent analysis shows that test-time resampling can recover per-instance selection headroom that no single-commit router captures; however, that guarantee holds only under an idealized oracle equipped with correctness labels and an unconstrained budget, neither of which a deployed system has. To the best of our knowledge, no previous work treats resampling the committed model and rerouting to an alternative model as competing uses of a single per-query cost budget. Therefore, this work formulates budget-aware test-time model selection: given a per-query budget and an imperfect verifier, allocate each unit of budget between resampling and rerouting so that expected correctness is maximized. An online resample-or-reroute (RoR) allocation policy driven by estimated marginal correctness per unit cost is proposed, and its behavior is grounded in the recoverability asymmetry between selection and sampling. Replay experiments on newly regenerated multi-draw correctness tensors from an eleven-model open-weight pool over four benchmarks of differing difficulty show that the proposed RoR policy attains a favorable cost-quality Pareto front relative to single-route, one-commit-router, budget-aware best-of-K, cascade, and random-allocation baselines for the tested pools, with the largest gains on the most heterogeneous benchmark; an ablation further shows the gains are verifier-gated, shrinking as verifier quality degrades, and robustness replays under a provider price vector and a label-free agreement verifier delineate where the conclusions carry over.
When a language model fails to answer a query on the first attempt, an agentic system retries, consuming additional tokens each time. This retry overhead creates a gap between what a model's per-token price implies and what a full workflow actually costs. We call this gap \emph{token inflation} and define it as the ratio of true workflow cost to single-call cost. Systems like FrugalGPT route based on the latter, which can underestimate real cost by more than $2\times$ on difficult tasks. We address this with InflationAgent, a four-stage router that (1) measures token inflation systematically across model tiers and task types, finding inflation as high as $4.25\times$ for a 7B model on multi-hop question answering; (2) introduces CoT Branching Entropy (CBE), a pre-execution difficulty signal computed entirely from local inference, which predicts high inflation with AUROC 0.887; and (3) selects models by maximizing a Semantic Exchange Rate (SER) that divides expected accuracy by predicted true cost, with a fresh-escalation policy that discards failed chains before routing to a stronger model. On GSM8K under a fixed budget, InflationAgent achieves 94.7\% accuracy versus 91.0\% for FrugalGPT while using 31\% fewer tokens, and we show that forwarding a failed reasoning chain to GPT-4o reduces its accuracy by up to 34.8 percentage points, validating the fresh-escalation design.
Edge-cloud inference collaborations are often designed with a routing estimator that decides whether to offload each frame from weak models at the edge to stronger models in the cloud. Existing systems place the routing estimator after the weak detector, so the weak forward pass still runs even on frames that are later offloaded. In this paper, we argue that this weak-conditioned design can be suboptimal when the offload budget varies. First, we present a competitive weak-skipping estimator (0.153 GFLOPs, about 29x lighter than the weak detector at 4.49 GFLOPs) that extracts routing signal from raw pixels, outperforming the common after-weak placement weak-conditioned baselines. Second, we show that neither weak-skipping nor weak-conditioned placement dominates across the full operating curve, and we propose budget-adaptive routing, which selects between them by offload budget via two offline-tuned thresholds. On PASCAL VOC, our budget-adaptive router traces the upper accuracy envelope of both fixed placements across the operating range. Our method reduces per-frame latency by up to 19.1 ms (about 30% lower at rho = 0.9). Besides outperforming SOTA methods, it is surprisingly stronger than the strong model (+1.7 pp over the strong model's peak mAP) at some operating points with far less compute. Artifacts are available at https://github.com/ViGeng/bgt-ada
Large multimodal models have achieved strong reasoning on complex visual tasks, but their inference efficiency is often restricted by long chains of thought. A promising solution is to pair a small draft model with a large target model, enabling cooperative inference employing a routing signal that adaptively routes queries to either the draft or target model based on their difficulties for optimal efficiency and accuracy. Yet, the remaining bottleneck is to establish a reliable query difficulty signal under multimodal settings. Existing approaches designed for language models either rely on post-hoc token probabilities, which fall short in multimodal scenarios, or depend on supervised fine-tuning, which is a data-sensitive strategy. Both paradigms perform routing only after a complete output, and ignore whether the target model can actually solve the routed instances. To address this, we propose PRP, a Proactive Routing Paradigm that enables early decision-making by jointly evaluating the competence of both the draft and target models. Our Draft Rating Learning (DRL) equips the draft model with an internal confidence estimator, while Joint Rating Learning (JRL) predicts how well the target model can handle a given query, thereby prioritizing the allocation of samples it excels at rather than the hardest ones. These ratings enable fine-grained, instance-level \textbf{Proactive Routing} and substantially accelerate inference without compromising overall performance. Extensive experiments across multiple multimodal reasoning benchmarks validate our effectiveness and efficiency.
Kaiyi Zhang, Xueliang Zhao, Zhuocheng Gong +2cs.CL
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%.
A synthetic measurement of model competence is useful only if it survives the move to real data, yet the real labels that would verify it are exactly what medical imaging lacks. We ask whether transfer can be predicted in advance, label-free, and answer with a mechanism: on synthetic digital twins, competence that is donor-driven (a property of the transplanted nodule) survives the synthetic to real change of host, while host-driven competence (a property of the surrounding anatomy) need not. We test this on three lung CT vision-language tasks chosen to span that axis, across five public VLMs, four guidance conditions, and seven real datasets. The prediction holds in every case: presence and size orderings transfer (R2 >= 0.96), lobe does not; the split survives leave-source-out calibration, and the diagnostic names that boundary before any real label. TrialCouncil, a training-free council calibrated only on synthetic CT, confirms it by matching the best fixed model exactly where transfer is predicted. The contribution is not the router but the finding that transfer itself is predictable, label-free, from synthetic data alone.
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.