{"total":23,"rows":[{"id":"2412.06126","title":"UCB algorithms for multi-armed bandits: Precise regret and adaptive inference","created":"2024-12-09","cited_by_count":19,"area":null},{"id":"2504.16728","title":"IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery","created":"2025-04-23","cited_by_count":19,"area":null},{"id":"2404.07732","title":"Monte Carlo Tree Search with Boltzmann Exploration","created":"2024-04-11","cited_by_count":12,"area":null},{"id":"2602.12966","title":"ProbeLLM: Automating Principled Diagnosis of LLM Failures","created":"2026-02-13","cited_by_count":9,"area":null},{"id":"2604.24537","title":"Stochastic simultaneous optimistic optimization","created":"2026-04-27","cited_by_count":8,"area":null},{"id":"2202.07071","title":"A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2305.09840","title":"Scale-Adaptive Balancing of Exploration and Exploitation in Classical Planning","created":"2023-05-16","cited_by_count":4,"area":null},{"id":"2103.13860","title":"Active Inference Tree Search in Large POMDPs","created":"2021-03-25","cited_by_count":2,"area":null},{"id":"2212.05208","title":"Lookahead Pathology in Monte-Carlo Tree Search","created":"2022-12-10","cited_by_count":2,"area":null},{"id":"2405.04407","title":"Super-Exponential Regret for UCT, AlphaGo and Variants","created":"2024-05-07","cited_by_count":2,"area":null},{"id":"2406.02871","title":"Sound Heuristic Search Value Iteration for Undiscounted POMDPs with Reachability Objectives","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2506.07276","title":"Tokenized Bandit for LLM Decoding and Alignment","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2604.19695","title":"Planning in entropy-regularized Markov decision processes and games","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2412.05196","title":"Exponential Speedups by Rerooting Levin Tree Search","created":"2024-12-06","cited_by_count":1,"area":null},{"id":"2604.18312","title":"Scale-free adaptive planning for deterministic dynamics & discounted rewards","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2609.06484","title":"Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing","created":"2026-09-06","cited_by_count":1,"area":null},{"id":"2406.16151","title":"Improved Monte Carlo Planning via Causal Disentanglement for Structurally-Decomposed Markov Decision Processes","created":"2024-06-23","cited_by_count":0,"area":null},{"id":"2506.21996","title":"AlphaBeta is not as good as you think: a simple class of synthetic games for a better analysis of deterministic game-solving algorithms","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2509.13132","title":"An Uncertainty-Weighted Decision Transformer for Navigation in Dense, Complex Driving Scenarios","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2601.22600","title":"An Efficient Algorithm for Thresholding Monte Carlo Tree Search","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.15110","title":"Sampling-guided exploration of active feature selection policies","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2605.03493","title":"Bandits on graphs and structures","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2608.07922","title":"Memory--Batch Tradeoffs in Lipschitz Bandits","created":"2026-08-08","cited_by_count":0,"area":null}],"next_cursor":null}