{"total":75,"rows":[{"id":"2309.17179","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","created":"2023-09-29","cited_by_count":295,"area":"lr"},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112,"area":"agents"},{"id":"2404.01230","title":"LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models","created":"2024-04-01","cited_by_count":99,"area":"lr"},{"id":"2402.16153","title":"ChatMusician: Understanding and Generating Music Intrinsically with LLM","created":"2024-02-25","cited_by_count":68,"area":null},{"id":"2501.09781","title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos","created":"2025-01-16","cited_by_count":43,"area":null},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42,"area":null},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2406.00877","title":"Evidence of Learned Look-Ahead in a Chess-Playing Neural Network","created":"2024-06-02","cited_by_count":34,"area":null},{"id":"2408.15971","title":"BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems","created":"2024-08-28","cited_by_count":26,"area":"agents"},{"id":"2409.20553","title":"Maia-2: A Unified Model for Human-AI Alignment in Chess","created":"2024-09-30","cited_by_count":25,"area":null},{"id":"2405.19946","title":"Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf","created":"2024-05-30","cited_by_count":24,"area":null},{"id":"2409.18433","title":"Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization","created":"2024-09-27","cited_by_count":24,"area":null},{"id":"2412.03920","title":"A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios","created":"2024-12-05","cited_by_count":23,"area":"agents"},{"id":"2412.01800","title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2311.09241","title":"Chain of Images for Intuitively Reasoning","created":"2023-11-09","cited_by_count":21,"area":"lr"},{"id":"2406.11741","title":"Transcendence: Generative Models Can Outperform The Experts That Train Them","created":"2024-06-17","cited_by_count":20,"area":null},{"id":"2410.05254","title":"GLEE: A Unified Framework and Benchmark for Language-based Economic Environments","created":"2024-10-07","cited_by_count":20,"area":null},{"id":"2402.07157","title":"Natural Language Reinforcement Learning","created":"2024-02-11","cited_by_count":17,"area":"lr"},{"id":"2405.15821","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition","created":"2024-05-23","cited_by_count":16,"area":"agents"},{"id":"2501.17186","title":"Complete Chess Games Enable LLM Become A Chess Master","created":"2025-01-26","cited_by_count":16,"area":null},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"area":null},{"id":"2311.07387","title":"Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Study","created":"2023-11-13","cited_by_count":15,"area":null},{"id":"2512.01992","title":"LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess","created":"2025-12-01","cited_by_count":15,"area":"lr"},{"id":"2505.23977","title":"VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL","created":"2025-05-29","cited_by_count":12,"area":"lr"},{"id":"2410.03893","title":"Human-aligned Chess with a Bit of Search","created":"2024-10-04","cited_by_count":11,"area":null},{"id":"2502.19805","title":"Implicit Search via Discrete Diffusion: A Study on Chess","created":"2025-02-27","cited_by_count":11,"area":"diffusion"},{"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":"2510.23948","title":"ChessQA: Evaluating Large Language Models for Chess Understanding","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2410.20811","title":"Bridging the Gap between Expert and Language Models: Concept-guided Chess Commentary Generation and Evaluation","created":"2024-10-28","cited_by_count":6,"area":null},{"id":"2503.15235","title":"Exploring Large Language Models for Word Games:Who is the Spy?","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2410.02829","title":"LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents","created":"2024-10-01","cited_by_count":5,"area":"agents"},{"id":"2411.14251","title":"Natural Language Reinforcement Learning","created":"2024-11-21","cited_by_count":5,"area":"lr"},{"id":"2412.17707","title":"SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC","created":"2024-12-23","cited_by_count":5,"area":"deeprl"},{"id":"2510.06475","title":"PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2605.24375","title":"Distilling Game Code World Model Generation into Lightweight Large Language Models","created":"2026-05-23","cited_by_count":5,"area":"wm"},{"id":"2607.16097","title":"Understanding Reasoning from Pretraining to Post-Training","created":"2026-07-17","cited_by_count":5,"area":"lr"},{"id":"2402.04154","title":"Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction","created":"2024-02-06","cited_by_count":4,"area":"offlinerl"},{"id":"2506.23068","title":"Curious Causality-Seeking Agents Learn Meta Causal World","created":"2025-06-29","cited_by_count":4,"area":"wm"},{"id":"2606.09826","title":"OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics","created":"2026-06-08","cited_by_count":4,"area":"agents"},{"id":"2410.14890","title":"Reasoning, Memorization, and Fine-Tuning Language Models for Non-Cooperative Games","created":"2024-10-18","cited_by_count":3,"area":"lr"},{"id":"2505.18607","title":"From Entity-Centric to Goal-Oriented Graphs: Enhancing LLM Knowledge Retrieval in Minecraft","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2509.24239","title":"ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2412.11417","title":"RL-LLM-DT: An Automatic Decision Tree Generation Method Based on RL Evaluation and LLM Enhancement","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2505.20120","title":"Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Markets","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.19095","title":"Baba is LLM: Reasoning in a Game with Dynamic Rules","created":"2025-06-23","cited_by_count":2,"area":"lr"},{"id":"2509.12927","title":"HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making","created":"2025-09-16","cited_by_count":2,"area":"agents"},{"id":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2405.06499","title":"Aspect-based Sentiment Evaluation of Chess Moves (ASSESS): an NLP-based Method for Evaluating Chess Strategies from Textbooks","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2410.00519","title":"Exploring the Learning Capabilities of Language Models using LEVERWORLDS","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2503.13980","title":"Empowering LLMs in Decision Games through Algorithmic Data Synthesis","created":"2025-03-18","cited_by_count":1,"area":"synth"},{"id":"2505.17512","title":"Is Your LLM Really Mastering the Concept? A Multi-Agent Benchmark","created":"2025-05-23","cited_by_count":1,"area":"agents"},{"id":"2510.18483","title":"StarBench: A Turn-Based RPG Benchmark for Agentic Multimodal Decision-Making and Information Seeking","created":"2025-10-21","cited_by_count":1,"area":"agents"},{"id":"2601.16471","title":"Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.04447","title":"Mixture of Masters: Sparse Chess Language Models with Player Routing","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2604.07752","title":"MIMIC-Py: An Extensible Tool for Personality-Driven Automated Game Testing with Large Language Models","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.09027","title":"GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives","created":"2026-05-09","cited_by_count":1,"area":"agents"},{"id":"2609.00474","title":"Exploring Collaboration between a language and a non-language agent","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2410.05347","title":"Bridging Local and Global Knowledge via Transformer in Board Games","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2412.03359","title":"WiS Platform: Enhancing Evaluation of LLM-Based Multi-Agent Systems Through Game-Based Analysis","created":"2024-12-04","cited_by_count":0,"area":"agents"},{"id":"2507.14520","title":"What if Othello-Playing Language Models Could See?","created":"2025-07-19","cited_by_count":0,"area":null},{"id":"2511.03724","title":"Outbidding and Outbluffing Elite Humans: Mastering Liar's Poker via Self-Play and Reinforcement Learning","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2603.25405","title":"System Design for Maintaining Internal State Consistency in Long-Horizon Robotic Tabletop Games","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.21896","title":"Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models","created":"2026-04-23","cited_by_count":0,"area":"agents"},{"id":"2605.17565","title":"Generalization or Memorization? Brittleness Testing for Chess-Trained Language Models","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.04202","title":"SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2606.23668","title":"On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.11486","title":"Communicating Chess Strategies in Natural Language","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.04240","title":"Hallucinations on the Board: Tool-Augmented Evaluation of LLM Chess Commentary","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.12626","title":"LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2608.14851","title":"Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.18286","title":"What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2610.00416","title":"Benchmarking Prompt Optimization of Large Language Models With Chess","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02425","title":"Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.04098","title":"Representation-Aligned Auxiliary Supervision for Language Model Adaptation","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}