Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation

• URL: http://arxiv.org/abs/2608.20316v2
• Date: Fri, 21 Aug 2026 18:08:50 GMT
• Title: Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
• Abstract summary: Heterogeneous AI systems can improve quality and efficiency by routing queries to the specialist who can answer most effectively at the lowest cost.<n>We formalize this tradeoff as an instance of Pandora's Box, the classical problem of optimal search with costly inspection.<n>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.
• Score: 64.51088225051959
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• ScaleSense: Cost-Intelligent Scaling Framework via Learned Resource Estimation in Alibaba AnalyticDB [59.708423132520515]
  Cloud-native serverless data warehouses achieve fine-grained elasticity by decoupling storage from compute.<n>Yet determining the optimal resource allocation for highly heterogeneous ad-hoc queries remains a formidable industrial challenge.<n>We propose ScaleSense, a proactive, query-level resource scaling framework.
  arXiv  Detail & Related papers  (2026-08-08T06:10:35Z)
• When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost [11.216720435946804]
  Budget-aware Active RAG evaluations should report frontiers, realized usage, threshold-transfer error, harm rates, and cost decompositions alongside accuracy.<n>We operationalize three questions that single-point evaluations conflate: whether trigger scores rank useful retrieval decisions, whether thresholds calibrated on past data meet future budgets, and how trigger-side changes deployment cost.
  arXiv  Detail & Related papers  (2026-07-27T05:17:06Z)
• Resample or Reroute? Budget-Aware Test-Time Model Selection for Large Language Models [0.10152838128195468]
  This work formulates budget-aware test-time model selection for large language models.<n>Online resample-or-reroute (RoR) allocation policy driven by estimated marginal correctness per unit cost is proposed.<n> experiments on newly regenerated 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 robustness front relative to single-route, one-commit-router, budget-aware best-of-K, cascade, and random-allocation baselines.
  arXiv  Detail & Related papers  (2026-07-09T16:34:15Z)
• Instance-Optimal Estimation with Multiple LLM Judges on a Budget [84.31744861038106]
  We formalize this question as *budgeted heteroskedastic multi-judge estimation*.<n>Given $K$ prompt-response pairs, $J$ judges with known costs, and unknown query-judge variances, the goal is to estimate a bounded score vector while minimizing an $ell_p$-error.<n>We prove that EST-IVWE matches the oracle IVWE rate up to lower-order terms in the budget.
  arXiv  Detail & Related papers  (2026-05-22T08:26:08Z)
• Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems [54.916243942641444]
  Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications.<n>We study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline.
  arXiv  Detail & Related papers  (2025-12-23T03:10:09Z)
• e1: Learning Adaptive Control of Reasoning Effort [88.51897900019485]
  Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning.<n>Users may prefer to allocate different amounts of reasoning effort depending on how they value output quality versus latency and cost.<n>We propose Adaptive Effort Control, a self-adaptive reinforcement learning method that trains models to use a user-specified fraction of tokens.
  arXiv  Detail & Related papers  (2025-10-30T23:12:21Z)
• Meta-Router: Bridging Gold-standard and Preference-based Evaluations in Large Language Model Routing [15.724480880994259]
  A large language model (LLM) router selects the most appropriate model from a pool of candidates for each query.<n> preference-based data, collected via crowdsourcing or LLM-as-a-judge systems, are cheaper and more scalable, yet often biased in reflecting the true quality of responses.<n>We develop an integrative causal router training framework that corrects preference-data bias, address imbalances between two data sources, and improve routing robustness and efficiency.
  arXiv  Detail & Related papers  (2025-09-29T21:44:00Z)
• Estimating Treatment Effects under Recommender Interference: A Structured Neural Networks Approach [32.55211271796683]
  We show that commonly adopted difference-in-means estimators can lead to severely biased estimates due to recommender interference.<n>We propose a recommender choice model'' that explicitly represents the interference pathway.<n>We validate our method with a large-scale field experiment on Weixin short-video platform.
  arXiv  Detail & Related papers  (2024-06-20T14:53:26Z)
• Cost-Efficient Online Hyperparameter Optimization [94.60924644778558]
  We propose an online HPO algorithm that reaches human expert-level performance within a single run of the experiment. Our proposed online HPO algorithm reaches human expert-level performance within a single run of the experiment, while incurring only modest computational overhead compared to regular training.
  arXiv  Detail & Related papers  (2021-01-17T04:55:30Z)
• Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards [24.983866845065926]
  We consider multi-armed bandits with heavy-tailed rewards, whose $p$-th moment is bounded by a constant $nu_p$ for $1pleq2$. We propose a novel robust estimator which does not require $nu_p$ as prior information. We show that an error probability of the proposed estimator decays exponentially fast.
  arXiv  Detail & Related papers  (2020-10-24T10:44:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.