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: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
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: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:2609.24969v1 Announce Type: new
Abstract: As agents are deployed with increased autonomy, even extremely rare events along their stochastic output trajectories can occur and prove catastrophic....
By Hanming Yang, Daksh Mittal, Jing Dong, Hongseok Namkoong
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
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:2605. 06605v2 Announce Type: replace Abstract: Evaluating and predicting the performance of large language models (LLMs) in multi-turn conversational settings is critical yet computationally expensive; key events -- e.
By Shai Feldman, Yaniv Romano
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
arXiv:2610.20293v1 Announce Type: cross
Abstract: Large language models increasingly generate multiple retrieval actions jointly, while downstream systems often provide only one reward for the result...
By Xinyi Cheng, Tianfu Zhang, Jiwen Li, Xuesen Zhang, Shihao Yu, Pengfei Zhu, Renhuan, Heda Wang
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:2609. 29140v1 Announce Type: new Abstract: Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty.
By Yezhou Cheng, Runjia Du, Zeming Liu, Qibai Chen, Hang Lyu, Yilan Wei, Yankai Zeng, Bojun Lin