{"list":"other","total":150,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2408.14837","title":"Diffusion Models Are Real-Time Game Engines","created":"2024-08-27","cited_by_count":296},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"1907.13440","title":"MineRL: A Large-Scale Dataset of Minecraft Demonstrations","created":"2019-07-29","cited_by_count":215},{"id":"2509.02544","title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","created":"2025-09-02","cited_by_count":215},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2508.13009","title":"Matrix-game 2.0: An open-source real-time and streaming interactive world model","created":"2025-08-18","cited_by_count":186},{"id":"1507.08750","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","created":"2015-07-31","cited_by_count":172},{"id":"2512.14614","title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","created":"2025-12-16","cited_by_count":170},{"id":"1909.05398","title":"Interactive Fiction Games: A Colossal Adventure","created":"2019-09-11","cited_by_count":168},{"id":"2510.10125","title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","created":"2025-10-11","cited_by_count":167},{"id":"2310.18940","title":"Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game","created":"2023-10-29","cited_by_count":152},{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146},{"id":"2501.08325","title":"GameFactory: Creating New Games with Generative Interactive Videos","created":"2025-01-14","cited_by_count":130},{"id":"2310.01557","title":"SmartPlay: A Benchmark for LLMs as Intelligent Agents","created":"2023-10-02","cited_by_count":125},{"id":"1903.03094","title":"Learning to Speak and Act in a Fantasy Text Adventure Game","created":"2019-03-07","cited_by_count":122},{"id":"2403.03186","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","created":"2024-03-05","cited_by_count":117},{"id":"2604.08995","title":"Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory","created":"2026-04-10","cited_by_count":100},{"id":"2306.00937","title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","created":"2023-06-01","cited_by_count":97},{"id":"2504.08388","title":"MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft","created":"2025-04-11","cited_by_count":97},{"id":"2406.06613","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","created":"2024-06-07","cited_by_count":95},{"id":"1906.02500","title":"Towards Interpretable Reinforcement Learning Using Attention Augmented Agents","created":"2019-06-06","cited_by_count":82},{"id":"2312.11865","title":"Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach","created":"2023-12-19","cited_by_count":79},{"id":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71},{"id":"2511.09515","title":"WMPO: World Model-based Policy Optimization for Vision-Language-Action Models","created":"2025-11-12","cited_by_count":70},{"id":"2310.03903","title":"LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models","created":"2023-10-05","cited_by_count":68},{"id":"2403.11807","title":"How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments","created":"2024-03-18","cited_by_count":67},{"id":"2505.15146","title":"lmgame-Bench: How Good are LLMs at Playing Games?","created":"2025-05-21","cited_by_count":55},{"id":"2305.13455","title":"Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents","created":"2023-05-22","cited_by_count":54},{"id":"2104.04258","title":"Counter-Strike Deathmatch with Large-Scale Behavioural Cloning","created":"2021-04-09","cited_by_count":50},{"id":"2310.05036","title":"AvalonBench: Evaluating LLMs Playing the Game of Avalon","created":"2023-10-08","cited_by_count":47},{"id":"2602.22208","title":"Solaris: Building a Multiplayer Video World Model in Minecraft","created":"2026-02-25","cited_by_count":47},{"id":"2402.02330","title":"Enhance Reasoning for Large Language Models in the Game Werewolf","created":"2024-02-04","cited_by_count":46},{"id":"2407.13943","title":"Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction","created":"2024-07-18","cited_by_count":45},{"id":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42},{"id":"2401.10568","title":"CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents","created":"2024-01-19","cited_by_count":42},{"id":"2502.20073","title":"Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents","created":"2025-02-27","cited_by_count":41},{"id":"1802.10217","title":"Investigating Human Priors for Playing Video Games","created":"2018-02-28","cited_by_count":39},{"id":"2603.24621","title":"ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence","created":"2026-03-24","cited_by_count":37},{"id":"2310.08367","title":"MCU: An Evaluation Framework for Open-Ended Game Agents","created":"2023-10-12","cited_by_count":34},{"id":"2412.06394","title":"GameArena: Evaluating LLM Reasoning through Live Computer Games","created":"2024-12-09","cited_by_count":32},{"id":"2505.13886","title":"Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning","created":"2025-05-20","cited_by_count":32},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31},{"id":"2512.04797","title":"SIMA 2: A Generalist Embodied Agent for Virtual Worlds","created":"2025-12-04","cited_by_count":31},{"id":"2407.00114","title":"OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents","created":"2024-06-27","cited_by_count":30},{"id":"2505.13426","title":"G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning","created":"2025-05-19","cited_by_count":29},{"id":"2503.16365","title":"JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse","created":"2025-03-20","cited_by_count":28},{"id":"2604.07429","title":"GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents","created":"2026-04-08","cited_by_count":28},{"id":"2601.02427","title":"NitroGen: An Open Foundation Model for Generalist Gaming Agents","created":"2026-01-04","cited_by_count":27},{"id":"2510.04542","title":"Code World Models for General Game Playing","created":"2025-10-06","cited_by_count":26},{"id":"2312.02519","title":"Creative Agents: Empowering Agents with Imagination for Creative Tasks","created":"2023-12-05","cited_by_count":24},{"id":"2409.12889","title":"Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case","created":"2024-09-19","cited_by_count":24},{"id":"2510.23691","title":"Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents","created":"2025-10-27","cited_by_count":24},{"id":"2503.06047","title":"DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments","created":"2025-03-08","cited_by_count":23},{"id":"2310.08922","title":"LLaMA Rider: Spurring Large Language Models to Explore the Open World","created":"2023-10-13","cited_by_count":21},{"id":"2412.05255","title":"TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft","created":"2024-12-06","cited_by_count":21},{"id":"2511.08892","title":"Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds","created":"2025-11-12","cited_by_count":21},{"id":"2410.17856","title":"ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting","created":"2024-10-23","cited_by_count":20},{"id":"2503.02358","title":"Are Large Vision Language Models Good Game Players?","created":"2025-03-04","cited_by_count":19},{"id":"2503.13217","title":"Dense Policy: Bidirectional Autoregressive Learning of Actions","created":"2025-03-17","cited_by_count":19},{"id":"2501.08328","title":"PokerBench: Training Large Language Models to become Professional Poker Players","created":"2025-01-14","cited_by_count":18},{"id":"2505.03792","title":"Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning","created":"2025-05-01","cited_by_count":18},{"id":"2412.13602","title":"GAMEBoT: Transparent Assessment of LLM Reasoning in Games","created":"2024-12-18","cited_by_count":17},{"id":"2501.17186","title":"Complete Chess Games Enable LLM Become A Chess Master","created":"2025-01-26","cited_by_count":16},{"id":"2506.08011","title":"Play to Generalize: Learning to Reason Through Game Play","created":"2025-06-09","cited_by_count":16},{"id":"2510.15414","title":"MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs","created":"2025-10-17","cited_by_count":16},{"id":"2502.04686","title":"Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization","created":"2025-02-07","cited_by_count":15},{"id":"2511.04898","title":"Real-Time Reasoning Agents in Evolving Environments","created":"2025-11-07","cited_by_count":15},{"id":"2512.01992","title":"LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess","created":"2025-12-01","cited_by_count":15},{"id":"2603.03447","title":"Proact-VL: A Proactive VideoLLM for Real-Time AI Companions","created":"2026-03-03","cited_by_count":15},{"id":"2410.00564","title":"Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining","created":"2024-10-01","cited_by_count":14}],"next_cursor":"100"}