{"total":101,"rows":[{"id":"2410.07927","title":"Efficient Reinforcement Learning with Large Language Model Priors","created":"2024-10-10","cited_by_count":30,"area":null},{"id":"2410.15644","title":"Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration","created":"2024-10-21","cited_by_count":22,"area":null},{"id":"2502.20508","title":"TripCraft: A Benchmark for Spatio-Temporally Fine Grained Travel Planning","created":"2025-02-27","cited_by_count":21,"area":null},{"id":"2506.15196","title":"HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges","created":"2025-06-18","cited_by_count":21,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2510.10035","title":"Failure-Driven Workflow Refinement","created":"2025-10-11","cited_by_count":20,"area":null},{"id":"2303.08060","title":"Beyond Games: A Systematic Review of Neural Monte Carlo Tree Search Applications","created":"2023-03-14","cited_by_count":16,"area":null},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2307.03290","title":"OmniBoost: Boosting Throughput of Heterogeneous Embedded Devices under Multi-DNN Workload","created":"2023-07-06","cited_by_count":12,"area":null},{"id":"2511.13211","title":"3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale","created":"2025-11-17","cited_by_count":12,"area":null},{"id":"2512.16424","title":"Synthelite: Chemist-aligned and feasibility-aware synthesis planning with LLMs","created":"2025-12-18","cited_by_count":10,"area":null},{"id":"2405.06758","title":"Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs","created":"2024-05-10","cited_by_count":9,"area":null},{"id":"2407.12021","title":"Adaptive Draft-Verification for Efficient Large Language Model Decoding","created":"2024-06-27","cited_by_count":9,"area":null},{"id":"2311.03583","title":"Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search","created":"2023-11-06","cited_by_count":8,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2510.21329","title":"TripTide: A Benchmark for Adaptive Travel Planning under Disruptions","created":"2025-10-24","cited_by_count":8,"area":null},{"id":"2210.13455","title":"Epistemic Monte Carlo Tree Search","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2312.16767","title":"Adaptive Anytime Multi-Agent Path Finding Using Bandit-Based Large Neighborhood Search","created":"2023-12-28","cited_by_count":7,"area":null},{"id":"2410.04683","title":"Towards Measuring Goal-Directedness in AI Systems","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2305.16209","title":"C-MCTS: Safe Planning with Monte Carlo Tree Search","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2109.13419","title":"The Role of Lookahead and Approximate Policy Evaluation in Reinforcement Learning with Linear Value Function Approximation","created":"2021-09-28","cited_by_count":5,"area":null},{"id":"2211.15068","title":"Learning to design without prior data: Discovering generalizable design strategies using deep learning and tree search","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2303.04651","title":"MCTS-GEB: Monte Carlo Tree Search is a Good E-graph Builder","created":"2023-03-08","cited_by_count":5,"area":null},{"id":"2311.00971","title":"An Integrated Framework Integrating Monte Carlo Tree Search and Supervised Learning for Train Timetabling Problem","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2502.03962","title":"Quantum Circuit Design using a Progressive Widening Enhanced Monte Carlo Tree Search","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2503.21383","title":"Controlling Large Language Model with Latent Actions","created":"2025-03-27","cited_by_count":5,"area":null},{"id":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2411.17867","title":"RankMap: Priority-Aware Multi-DNN Manager for Heterogeneous Embedded Devices","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2303.09449","title":"Proof Number Based Monte-Carlo Tree Search","created":"2023-03-16","cited_by_count":3,"area":null},{"id":"2401.05199","title":"Monte Carlo Tree Search for Recipe Generation using GPT-2","created":"2024-01-10","cited_by_count":3,"area":null},{"id":"2109.00619","title":"Learning compositional programs with arguments and sampling","created":"2021-09-01","cited_by_count":2,"area":null},{"id":"2112.07761","title":"Split Moves for Monte-Carlo Tree Search","created":"2021-12-14","cited_by_count":2,"area":null},{"id":"2206.01011","title":"Policy Gradient Algorithms with Monte Carlo Tree Learning for Non-Markov Decision Processes","created":"2022-06-02","cited_by_count":2,"area":null},{"id":"2210.11152","title":"Machine Learning for K-adaptability in Two-stage Robust Optimization","created":"2022-10-20","cited_by_count":2,"area":null},{"id":"2308.04719","title":"JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games","created":"2023-08-09","cited_by_count":2,"area":null},{"id":"2401.13770","title":"AlphaMapleSAT: An MCTS-based Cube-and-Conquer SAT Solver for Hard Combinatorial Problems","created":"2024-01-24","cited_by_count":2,"area":null},{"id":"2404.16364","title":"ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2406.09242","title":"Towards a Characterisation of Monte-Carlo Tree Search Performance in Different Games","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2409.13783","title":"A Value Based Parallel Update MCTS Method for Multi-Agent Cooperative Decision Making of Connected and Automated Vehicles","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2503.04148","title":"Ecomap: Sustainability-Driven Optimization of Multi-Tenant DNN Execution on Edge Servers","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2601.01392","title":"SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning","created":"2026-01-04","cited_by_count":2,"area":null},{"id":"2601.02196","title":"ACDZero: MCTS Agent for Mastering Automated Cyber Defense","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2602.14083","title":"Plan-MCTS: Plan Exploration for Action Exploitation in Web Navigation","created":"2026-02-15","cited_by_count":2,"area":null},{"id":"2109.06966","title":"Searching for More Efficient Dynamic Programs","created":"2021-09-14","cited_by_count":1,"area":null},{"id":"2110.05478","title":"An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design","created":"2021-10-10","cited_by_count":1,"area":null},{"id":"2203.09608","title":"Developing a Successful Bomberman Agent","created":"2022-03-17","cited_by_count":1,"area":null},{"id":"2204.12043","title":"An Efficient Dynamic Sampling Policy For Monte Carlo Tree Search","created":"2022-04-26","cited_by_count":1,"area":null},{"id":"2307.08024","title":"Bayesian inference for data-efficient, explainable, and safe robotic motion planning: A review","created":"2023-07-16","cited_by_count":1,"area":null},{"id":"2308.04292","title":"Engineering LaCAM$^\\ast$: Towards Real-Time, Large-Scale, and Near-Optimal Multi-Agent Pathfinding","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2308.14350","title":"Simple Modification of the Upper Confidence Bound Algorithm by Generalized Weighted Averages","created":"2023-08-28","cited_by_count":1,"area":null},{"id":"2401.17044","title":"Scalable Mechanism Design for Multi-Agent Path Finding","created":"2024-01-30","cited_by_count":1,"area":null},{"id":"2402.08511","title":"Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2406.09322","title":"Active Inference Meeting Energy-Efficient Control of Parallel and Identical Machines","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2408.05488","title":"Structure and Reduction of MCTS for Explainable-AI","created":"2024-08-10","cited_by_count":1,"area":null},{"id":"2409.18335","title":"A Fairness-Driven Method for Learning Human-Compatible Negotiation Strategies","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2411.07171","title":"Anytime Sequential Halving in Monte-Carlo Tree Search","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2505.05665","title":"Characterizing the Robustness of Black-Box LLM Planners Under Perturbed Observations with Adaptive Stress Testing","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2505.20011","title":"The Many Challenges of Human-Like Agents in Virtual Game Environments","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.13223","title":"Towards Explaining Monte-Carlo Tree Search by Using Its Enhancements","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2508.09142","title":"Bayesian-Driven Graph Reasoning for Active Radio Map Construction","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2510.01874","title":"Deep Hedging Under Non-Convexity: Limitations and a Case for AlphaZero","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2603.21530","title":"LLM-Based Test Case Generation in DBMS through Monte Carlo Tree Search","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.07042","title":"Planning Task Shielding: Detecting and Repairing Flaws in Planning Tasks through Turning them Unsolvable","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.08077","title":"Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.17285","title":"UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2608.06183","title":"MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2111.13770","title":"A Fast Evolutionary adaptation for MCTS in Pommerman","created":"2021-11-26","cited_by_count":0,"area":null},{"id":"2203.14963","title":"Deep Learning and Artificial General Intelligence: Still a Long Way to Go","created":"2022-03-25","cited_by_count":0,"area":null},{"id":"2210.05014","title":"Exploring Adaptive MCTS with TD Learning in miniXCOM","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2212.11360","title":"Feature Acquisition using Monte Carlo Tree Search","created":"2022-12-21","cited_by_count":0,"area":null},{"id":"2305.13206","title":"Know your Enemy: Investigating Monte-Carlo Tree Search with Opponent Models in Pommerman","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2308.08693","title":"AI planning in the imagination: High-level planning on learned abstract search spaces","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2401.12243","title":"Constraint-Generation Policy Optimization (CGPO): Nonlinear Programming for Policy Optimization in Mixed Discrete-Continuous MDPs","created":"2024-01-20","cited_by_count":0,"area":null},{"id":"2404.09304","title":"Monte Carlo Search Algorithms Discovering Monte Carlo Tree Search Exploration Terms","created":"2024-04-14","cited_by_count":0,"area":null},{"id":"2406.08687","title":"AlphaZeroES: Direct score maximization outperforms planning loss minimization","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2406.08766","title":"Injecting Combinatorial Optimization into MCTS: Application to the Board Game boop","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2407.13968","title":"Optimizing Agricultural Order Fulfillment Systems: A Hybrid Tree Search Approach","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2501.18455","title":"Conversation Games and a Strategic View of the Turing Test","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2502.01527","title":"Enhancing Bayesian Network Structural Learning with Monte Carlo Tree Search","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2506.13249","title":"Generalized Proof-Number Monte-Carlo Tree Search","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2507.01043","title":"Data Classification with Dynamically Growing and Shrinking Neural Networks","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2507.21589","title":"Exploring the Link Between Bayesian Inference and Embodied Intelligence: Toward Open Physical-World Embodied AI Systems","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2508.15220","title":"Locally Pareto-Optimal Interpretations for Black-Box Machine Learning Models","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2508.20140","title":"Array-Based Monte Carlo Tree Search","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.21902","title":"DyRo-MCTS: A Robust Monte Carlo Tree Search Approach to Dynamic Job Shop Scheduling","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.00876","title":"Unveiling Interesting Insights: Monte Carlo Tree Search for Knowledge Discovery","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.06381","title":"Monte Carlo Permutation Search","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2512.24829","title":"Explaining Why Things Go Where They Go: Interpretable Constructs of Human Organizational Preferences","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2512.24959","title":"Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learning","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2601.02649","title":"Effective Online 3D Bin Packing with Lookahead Parcels Using Monte Carlo Tree Search","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2602.22361","title":"Optimizing Neural Network Architecture for Medical Image Segmentation Using Monte Carlo Tree Search","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.03252","title":"Valet: A Standardized Testbed of Traditional Imperfect-Information Card Games","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.10512","title":"Resource-constrained Amazons chess decision framework integrating large language models and graph attention","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2605.07703","title":"Finite-Time Analysis of MCTS in Continuous POMDP Planning","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.16524","title":"Toward Template-Free Explainability for Monte Carlo Tree Search","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2607.13007","title":"Dynamic Resource Allocation for Ensemble Determinization MCTS","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.26946","title":"Belief-Guided Decision Making with Uncertainty Gating in the Game of Go","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.07544","title":"MOSAIC: Adversarial Co-evolution of Specialist Heuristics and Problem Instances for LLM-based Automated Heuristic Design","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.05207","title":"FluxDisco: Symbolic Regression for Stoichiometric Dynamical Systems via Monte Carlo Graph Search","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.12542","title":"Equal-Budget Monte Carlo Tree Search versus Randomized-Restart List Scheduling for DAG Workflows: A Controlled Equal-Budget Computational Study","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":"100"}