arXiv AI

Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets

arXiv Machine Learning
Sep 29

Offline Policy Evaluation as a decision support tool for designing Adaptive Experiments

The paper explores how data from fixed A/B tests can guide the deployment of adaptive experiments using contextual bandits. By combining off‑policy evaluation with a controlled warm‑start simulation, the authors rank pre‑specified adaptive and non‑adaptive policies using doubly robust estimators. Experiments on synthetic trials and real benchmarks show that adaptive, context‑aware policies outperform fixed allocations when heterogeneity exists, but offer little advantage otherwise.

By Jo\~ao Victor Ferreira Alves, Eduardo Rocha Laurentino, Gustavo de Oliveira Kanno, Thiago Costa Rizuti da Rocha
arXiv Machine Learning
Sep 30

Tail-Influence Sampling for CVaR Policy Evaluation

arXiv:2609.38096v1 Announce Type: new Abstract: Policies with similar mean returns can differ sharply in rare failures, yet estimating lower-tail conditional value-at-risk (CVaR) accurately can requi...

By Pauline Bourigault, Xiaotong Ji, Matthieu Zimmer, Rasul Tutunov, Haitham Bou-Ammar
arXiv Machine Learning
Oct 7

Dynamic Budget Allocation for LLM Evaluation under Hard Resource Constraints

The paper introduces HARP, a hard-budget allocation method for evaluating large language models (LLMs) in multi-turn interactions where the time-to-event is partially observed due to resource limits. HARP guarantees that the total computational budget is never exceeded, reallocates unused budget, and provides lower predictive bounds (LPBs) with finite-sample coverage and unbiased metric estimates. Experiments on tasks such as jailbreaks, toxic content, and hallucinations demonstrate that HARP achieves near-nominal coverage with low variance while respecting the fixed budget.

By Shai Feldman, Yaniv Romano
arXiv Computation and Language
Sep 15

When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis

arXiv:2609.15309v1 Announce Type: new Abstract: Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alternatives, and decide when to s...

By Kaiyuan Liu, Qiuyang Mang, Bo Peng, Wenhao Chai, Hanchen Li, Shreyas Pimpalgaonkar, Luke Zettlemoyer, Alex Dimakis, Alvin Cheung
arXiv Machine Learning
Jul 30

Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR

arXiv:2607. 26253v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all responses correct or all incorrect) whose zero reward variance yields no policy-gradient signal.

By Pixel Nomand, Elena Voss, Marcus Hale, Sofia Reyes
arXiv AI
Oct 9

Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation

The paper proposes a method for allocating limited counterfactual annotation resources from multiple sources—such as domain experts and large language models—to improve off-policy evaluation in contextual bandits. By formulating an integer optimization problem that balances source-specific costs and error rates, the authors derive a majorization‑minimization algorithm that iteratively reduces estimator variance. Experiments on synthetic clinical and education bandit data demonstrate that the optimized allocation cuts mean‑squared error by over 20% compared to no annotation.

By Biao Xiang, Ali Eshragh, Yuexing Li, Kai Wang
arXiv Computer Vision
Oct 28

How Much Can Best-of-N Help a World Action Model? Measuring Selectable Headroom and Realizing It in Closed Loop

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