The paper introduces a denoised counterfactual protocol to accurately measure the selectable headroom of world action models (WAMs) and uses these measurements to build a fail‑gated selector. Across four WAMs and two benchmarks, the study shows that the standard estimate overstates selectable headroom, that structured action perturbations can add up to 16 points of headroom, and that imagined futures retain candidate‑outcome information without loss. The selector improves closed‑loop task success from 76.9 % to 81.6 % on held‑out training episodes and from 62.6 % to 69.8 % on unseen tasks.
By Haojia Gao, Yue Cao, Yumin Liu, Haohua Que, Mingkai Liu, Guanqiu Guo, Zhuo Zou, Bokui Chen, Xueqian Wang
arXiv:2606. 04342v1 Announce Type: cross Abstract: Multi-step time series forecasting (MSF) is commonly evaluated using point-wise error metrics such as mean squared error (MSE), implicitly treating the conditional mean as a sufficient target.
By Riku Green, Zahraa S. Abdallah, Telmo M Silva Filho
Risk-budgeted throughput forecasting converts a point forecast of LEO satellite capacity into a conservative bound whose overestimation rate is held at a user-specified budget, so that admission contr...
arXiv:2610.14996v1 Announce Type: new
Abstract: Choosing a few robust algorithms or schedules can require evaluating every candidate under many adverse scenarios, even though an agent only needs to i...
By Yuhe Sui, Yingzhi Tang
The study reproduces the BG-CFQS risk‑controlled throughput forecasting method on three Starlink traces and an additional dataset, finding that its risk guarantees hold only under random data splits and fail under contiguous temporal splits. It also shows the method cannot support risk budgets below 0.15, that static conformal calibration does not improve ranking, and that group‑conditional online recalibration often performs worse than no conditioning. These empirical results question the practical reliability of the technique for real‑world satellite link admission control.
By Mayan Sharma, Kriti Saini, Devansh Behl, Suganya R, S. Vijayaragavan
arXiv:2607. 13048v1 Announce Type: cross Abstract: Streaming inference pipelines increasingly pair lightweight fast models with Large Language Models (LLMs) that provide rich semantic understanding at substantial cost.
By Zhaohui Wang
The paper introduces a formal framework and benchmark for time‑series world models (TSWMs) that separates state, actions, and exogenous inputs, and defines a new metric called mechanism consistency to evaluate whether model predictions move in the expected direction when actions change. Experiments on eight public datasets show that using a frozen latent prediction space and gated output fusion improves prediction accuracy, while prediction error and mechanism consistency often diverge, with the best‑performing models sometimes failing to exhibit consistent directional responses. Adding a directional supervision loss significantly boosts mechanism consistency without affecting mean‑absolute error, providing a practical recipe for building more reliable TSWMs.
By Haochen Zhang, Jiaheng Guo, Zhen Xu, Zachary Plotkin, Nicholas Konz, Zhen Tan, Tianlong Chen
The paper explores a new lossy strategy for speculative decoding called verifier skipping, which allows certain draft prefixes to be committed without invoking the verifier. It investigates which confidence signals—raw token confidence, learned marginal survival, or learned conditional survival—best schedule these skips, finding that raw confidence often performs best despite higher positionwise AUROC for learned signals. Experiments on HumanEval with DiffuCoder-7B-Instruct and Qwen3-32B show that all three signals can reduce verifier calls by 9.6% to 13.5% while maintaining the same pass@1 as Strict SDD.
By Haoxuan Luo, Jameson Sandler, Ferdinando Fioretto
The paper evaluates how well typed decision models, which output probability distributions, actually provide reliable guarantees. By comparing open-weight Laya and Jev 1.13 across 190 evaluations, the study finds that point‑estimate thresholds frequently break promised accuracy, while a Beta lower‑bound rule and Learn‑then‑Test approach maintain guarantees more consistently. The work also explores calibration across languages, the impact of noise, data requirements for fine‑tuning, and the limitations of confidence in predicting outcomes or providing faithful explanations.
By Pedro Carvalho Brom
arXiv:2608. 07809v1 Announce Type: new Abstract: A world model is only useful for physical AI if it changes what the agent does, and only safe if it declines to do so when it is wrong.
By Yiyao Zhang, Diksha Goel, Hussain Ahmad, Shixun Huang, Jun Shen
The paper introduces a Bayesian self‑escalation strategy for hierarchical large‑language‑model agents, allowing an agent to detect during its own reasoning that it is unlikely to succeed and hand control over to a stronger model. The authors formalise this as an optimal‑stopping problem over a learned competence posterior, derive a myopic escalation threshold, and prove that the optimal policy is a time‑varying threshold without assumptions on the raw signal. They provide theoretical guarantees—including a 1/√n regret decay with n calibration trajectories—and validate the approach in simulations and a real‑model code‑generation cascade, showing that the escalation frontier outperforms post‑hoc routing at equal cost.
whyItMatters":"The study offers a principled, theoretically grounded method for agents to dynamically decide when to seek stronger models, potentially improving efficiency and reliability in hierarchical LLM systems."
By Nadeem Shaikh
The paper introduces a method to certify selective prediction in machine learning systems by computing the availability of safety gates through exact-binomial inversion and dynamic programming. It demonstrates that a truth-informed planner can significantly improve mean coverage over naive approaches, and that reallocating error budgets further enhances coverage across diverse applications such as LLM tool‑calling, content moderation, lesion classification, and recommendation. The study highlights the importance of planning and finite‑sample estimation in ensuring reliable, granular deployment of selective predictors.
By Parivesh Priye, Yufeng Wang, Haibin Ling, Michael Chaykowsky