{"total":17,"rows":[{"id":"2504.07157","title":"GAAPO: Genetic Algorithmic Applied to Prompt Optimization","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2505.23260","title":"Stable Thompson Sampling: Valid Inference via Variance Inflation","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2412.08843","title":"Allocation Stability and Wald Inference under Variance-Aware UCB","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2602.07472","title":"Bandit Allocational Instability","created":"2026-02-07","cited_by_count":3,"area":null},{"id":"2503.04855","title":"A characterization of sample adaptivity in UCB data","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2512.20368","title":"Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stability","created":"2025-12-23","cited_by_count":2,"area":null},{"id":"2602.06014","title":"Optimism Stabilizes Thompson Sampling for Adaptive Inference","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2601.02683","title":"Learning from Prompt itself: the Hierarchical Attribution Prompt Optimization","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2602.21478","title":"Efficient Inference after Directionally Stable Adaptive Experiments","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2505.16918","title":"Scalable and Interpretable Contextual Bandits: A Literature Review and Retail Offer Prototype","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2604.11994","title":"Offline-Online Reinforcement Learning for Linear Mixture MDPs","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2606.00913","title":"Bandit Simulation for Average Reward Inference","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.01655","title":"MINTS: Minimalist Thompson Sampling","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.22639","title":"Statistical Inference for Misspecified Contextual Bandits","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.22935","title":"Discrepancy-Rounded Fair Bandits with Static and Time-Varying Exposure Floors","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.01069","title":"Sharp Characterization of Bias in Post-Bandit Inference","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.17841","title":"Toward the Optimal Regret-Instability Trade-off in Multi-Armed Bandits","created":"2026-08-18","cited_by_count":0,"area":null}],"next_cursor":null}