When Should a World Model Move? Loss-Conditioned State Execution

• URL: http://arxiv.org/abs/2609.15801v1
• Date: Mon, 14 Sep 2026 16:12:03 GMT
• Title: When Should a World Model Move? Loss-Conditioned State Execution
• Abstract summary: We introduce loss-conditioned state execution, a model-agnostic method that decides whether to execute a world model's fixed feasible proposal or retain the current state.<n>We formalize state movability as the existence of a loss-reducing feasible correction and distinguish it from the benefit of a particular proposal.<n>Experiments on public forecasting and action-conditioned dynamics benchmarks show supported updates and a trade-off between certification and coverage.
• Score: 4.142275163201261
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce loss-conditioned state execution, a model-agnostic method that decides whether to execute a world model's fixed feasible proposal or retain the current state. Predictive informativeness alone, however, does not establish whether an update will reduce downstream loss. Occurrence ranking can approach perfection while persistence remains the unique absolute-loss Bayes action. Two transition laws can also share occurrence information and conditional variance yet require opposite absolute-loss decisions. We formalize state movability as the existence of a loss-reducing feasible correction and distinguish it from the benefit of a particular proposal. Our method constructs a loss-specific feasible proposal from a predictive distribution and evaluates its groupwise bounded-loss gain over persistence on independent calibration units. The proposal is executed only in groups with a positive simultaneous lower confidence bound. For fixed proposals and groups with bounded unit losses, we prove that every accepted group has lower expected loss than persistence with high probability when calibration units are i.i.d. draws from the target population. Experiments on public forecasting and action-conditioned dynamics benchmarks show supported updates and a trade-off between certification and coverage. On 28,684 held-out M4 Monthly series, the method executes the proposal for 14.0% of series and achieves bounded loss 0.588, compared with 0.599 for persistence and 0.621 for always executing the proposal. The paired 95% bootstrap intervals for both comparisons lie below zero. In constrained forecasting of six unhealthy-inventory types from JD$\mbox{.}$com, a leading e-retailer in China, strong occurrence-ranking signal coexists with a loss-based preference for persistence, illustrating why event predictability and state execution must be evaluated separately.

Related papers

• Settling: Equilibrium Inference for Non-Convex Validity Sets [0.45687771576879593]
  Under squared loss, an ambiguous conditional distribution can have a single point estimate that is invalid.<n>We formalize this failure as conditional mean collapse and introduce Settling, an equilibrium-based operator that separates proposal generation, consistency evaluation, and test-time selection.
  arXiv  Detail & Related papers  (2026-09-09T03:57:24Z)
• Compute-Bounded Security Assurance - Coverage, Verification, and Response under Resource Constraints [0.0]
  Additional inference compute can increase the number of correctly resolved security-assurance tasks.<n>We develop a resource-constrained framework that separates success, unique coverage, accepted evidence, and operational protection.<n>A conceptual defensive architecture separates evidence analysis, adjudication, and operational authority.
  arXiv  Detail & Related papers  (2026-09-07T13:07:55Z)
• Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling [0.0]
  Synthetic-population tools run every individual as an independent large language model (LLM) agent.<n>We show that this paradigm has a basic failure mode, and we set a distribution-first corrective against it.
  arXiv  Detail & Related papers  (2026-07-17T15:45:57Z)
• YUKTI: From Natural-Language Situations to Robust, Verifiable Decisions An Uncertainty-Typed Proposition IR, Assumption-Robust Pareto Frontiers, and a Regret Certificate [0.0]
  We show that YUKTI routes each stage to an exact, nonlinear, or evolutionary solver.<n>We prove a bound making rho an exact factor of decision regret, add auditable traceability, and synthesize a benchmark-faithful data foundation.<n>We validate three ways: under controlled misspecification the robust compromise cuts mean and tail regret by over 90% versus a naive point plan; and on a regulated commercial decision we optimize inside a lawful action space and price the downside in euros.
  arXiv  Detail & Related papers  (2026-06-22T09:29:13Z)
• Towards Anytime-Valid Statistical Watermarking [63.02116925616554]
  We develop the first e-value-based watermarking framework, Anchored E-Watermarking, that unifies optimal sampling with anytime-valid inference.<n>Our framework can significantly enhance sample efficiency, reducing the average token budget required for detection by 13-15% relative to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-19T18:32:26Z)
• Monitoring State Transitions in Markovian Systems with Sampling Cost [65.4151496405543]
  A natural approach is a greedy policy that predicts when the expected prediction loss is below the query cost and queries otherwise.<n>We analyze this policy in a Markovian setting, where the optimal (OPT) strategy is a state-dependent threshold policy.<n>For the case of unknown transition probabilities, we propose a projected gradient descent (PSGD)-based learning variant of the greedy policy.
  arXiv  Detail & Related papers  (2025-10-25T15:07:37Z)
• Rejection via Learning Density Ratios [50.91522897152437]
  Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions.<n>We propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance.<n>Our framework is tested empirically over clean and noisy datasets.
  arXiv  Detail & Related papers  (2024-05-29T01:32:17Z)
• Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting [65.21599711087538]
  Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and test data by adapting a given model w.r.t. any test sample.<n>Prior methods perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications.<n>We propose an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples.
  arXiv  Detail & Related papers  (2024-03-18T05:49:45Z)
• Equal Opportunity of Coverage in Fair Regression [50.76908018786335]
  We study fair machine learning (ML) under predictive uncertainty to enable reliable and trustworthy decision-making. We propose Equal Opportunity of Coverage (EOC) that aims to achieve two properties: (1) coverage rates for different groups with similar outcomes are close, and (2) the coverage rate for the entire population remains at a predetermined level.
  arXiv  Detail & Related papers  (2023-11-03T21:19:59Z)
• Beyond calibration: estimating the grouping loss of modern neural networks [68.8204255655161]
  Proper scoring rule theory shows that given the calibration loss, the missing piece to characterize individual errors is the grouping loss. We show that modern neural network architectures in vision and NLP exhibit grouping loss, notably in distribution shifts settings.
  arXiv  Detail & Related papers  (2022-10-28T07:04:20Z)
• Counterfactual inference in sequential experiments [17.817769460838665]
  We consider after-study statistical inference for sequentially designed experiments wherein multiple units are assigned treatments for multiple time points.<n>Our goal is to provide inference guarantees for the counterfactual mean at the smallest possible scale.<n>We illustrate our theory via several simulations and a case study involving data from a mobile health clinical trial HeartSteps.
  arXiv  Detail & Related papers  (2022-02-14T17:24:27Z)
• Selective Regression Under Fairness Criteria [30.672082160544996]
  In some cases, the performance of minority group can decrease while we reduce the coverage. We show that such an unwanted behavior can be avoided if we can construct features satisfying the sufficiency criterion.
  arXiv  Detail & Related papers  (2021-10-28T19:05:12Z)

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.