{"total":73,"rows":[{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881,"area":"wm"},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634,"area":"wm"},{"id":"2502.08691","title":"AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society","created":"2025-02-12","cited_by_count":186,"area":"wm"},{"id":"2310.01361","title":"GenSim: Generating Robotic Simulation Tasks via Large Language Models","created":"2023-10-02","cited_by_count":125,"area":"wm"},{"id":"2306.12672","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","created":"2023-06-22","cited_by_count":119,"area":"wm"},{"id":"2402.12275","title":"WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment","created":"2024-02-19","cited_by_count":107,"area":"wm"},{"id":"2407.04363","title":"AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents","created":"2024-07-05","cited_by_count":102,"area":"wm"},{"id":"2510.16907","title":"VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents","created":"2025-10-19","cited_by_count":62,"area":"wm"},{"id":"2312.05230","title":"Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning","created":"2023-12-08","cited_by_count":60,"area":"wm"},{"id":"2403.12037","title":"MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control","created":"2024-03-18","cited_by_count":53,"area":"wm"},{"id":"2410.03645","title":"GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs","created":"2024-10-04","cited_by_count":52,"area":"wm"},{"id":"2404.10775","title":"COMBO: Compositional World Models for Embodied Multi-Agent Cooperation","created":"2024-04-16","cited_by_count":49,"area":"wm"},{"id":"2411.00114","title":"Project Sid: Many-agent simulations toward AI civilization","created":"2024-10-31","cited_by_count":49,"area":"wm"},{"id":"2602.22208","title":"Solaris: Building a Multiplayer Video World Model in Minecraft","created":"2026-02-25","cited_by_count":47,"area":"wm"},{"id":"2405.15383","title":"Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search","created":"2024-05-24","cited_by_count":40,"area":"wm"},{"id":"2509.20021","title":"Embodied AI: From LLMs to World Models","created":"2025-09-24","cited_by_count":24,"area":"wm"},{"id":"2602.05842","title":"Reinforcement World Model Learning for LLM-based Agents","created":"2026-02-05","cited_by_count":24,"area":"wm"},{"id":"2506.01622","title":"General agents contain world models","created":"2025-06-02","cited_by_count":17,"area":"wm"},{"id":"2310.12690","title":"Neurosymbolic Grounding for Compositional World Models","created":"2023-10-19","cited_by_count":14,"area":"wm"},{"id":"2410.03618","title":"Open-World Reinforcement Learning over Long Short-Term Imagination","created":"2024-10-04","cited_by_count":13,"area":"wm"},{"id":"2510.12088","title":"One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration","created":"2025-10-14","cited_by_count":10,"area":"wm"},{"id":"2411.07690","title":"World Models: The Safety Perspective","created":"2024-11-12","cited_by_count":9,"area":"wm"},{"id":"2604.02580","title":"VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation","created":"2026-04-02","cited_by_count":8,"area":"wm"},{"id":"2607.01531","title":"OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3","created":"2026-07-01","cited_by_count":8,"area":"wm"},{"id":"2512.23676","title":"Web World Models","created":"2025-12-29","cited_by_count":7,"area":"wm"},{"id":"2406.07381","title":"World Models with Hints of Large Language Models for Goal Achieving","created":"2024-06-11","cited_by_count":6,"area":"wm"},{"id":"2504.15785","title":"WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents","created":"2025-04-22","cited_by_count":5,"area":"wm"},{"id":"2602.03146","title":"General Agents Contain World Models, even under Partial Observability and Stochasticity","created":"2026-02-03","cited_by_count":5,"area":"wm"},{"id":"2608.14490","title":"Twin: Playing an Unknown Game with a Test-Time Digital Twin","created":"2026-08-14","cited_by_count":4,"area":"wm"},{"id":"2608.16859","title":"HarnessEval-W: Agentifying the Evaluation of Visual Worlds","created":"2026-08-17","cited_by_count":4,"area":"wm"},{"id":"2503.24388","title":"RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy","created":"2025-03-31","cited_by_count":3,"area":"wm"},{"id":"2608.25518","title":"Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models","created":"2026-08-26","cited_by_count":3,"area":"wm"},{"id":"2609.16679","title":"AI for Games in the Foundation Model Era","created":"2026-09-15","cited_by_count":3,"area":"wm"},{"id":"2411.15998","title":"PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision Making","created":"2024-11-24","cited_by_count":2,"area":"wm"},{"id":"2511.15407","title":"IPR-1: Interactive Physical Reasoner","created":"2025-11-19","cited_by_count":2,"area":"wm"},{"id":"2605.12178","title":"Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics","created":"2026-05-12","cited_by_count":2,"area":"wm"},{"id":"2606.07127","title":"Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes","created":"2026-06-05","cited_by_count":2,"area":"wm"},{"id":"2606.12780","title":"ProPlay: Procedural World Models for Self-Evolving LLM Agents","created":"2026-06-11","cited_by_count":2,"area":"wm"},{"id":"2608.07107","title":"MemWM: Memory-Augmented Text-Based World Model","created":"2026-08-07","cited_by_count":2,"area":"wm"},{"id":"2609.01861","title":"Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimization","created":"2026-09-01","cited_by_count":2,"area":"wm"},{"id":"2403.15698","title":"SceneX: Procedural Controllable Large-scale Scene Generation","created":"2024-03-23","cited_by_count":1,"area":"wm"},{"id":"2406.00765","title":"The Embodied World Model Based on LLM with Visual Information and Prediction-Oriented Prompts","created":"2024-06-02","cited_by_count":1,"area":"wm"},{"id":"2509.04731","title":"Generative World Models of Tasks: LLM-Driven Hierarchical Scaffolding for Embodied Agents","created":"2025-09-05","cited_by_count":1,"area":"wm"},{"id":"2602.00608","title":"Scalable Generative Game Engine: Breaking the Resolution Wall via Hardware-Algorithm Co-Design","created":"2026-01-31","cited_by_count":1,"area":"wm"},{"id":"2602.02799","title":"Joint Learning of Hierarchical Neural Options and Abstract World Model","created":"2026-02-02","cited_by_count":1,"area":"wm"},{"id":"2605.12289","title":"PriorZero: Bridging Language Priors and World Models for Decision Making","created":"2026-05-12","cited_by_count":1,"area":"wm"},{"id":"2605.16725","title":"Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models","created":"2026-05-16","cited_by_count":1,"area":"wm"},{"id":"2606.31422","title":"Ask the World Before Acting: Environment Probing for Calibrated Agent World Models","created":"2026-06-30","cited_by_count":1,"area":"wm"},{"id":"2607.11689","title":"From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence","created":"2026-07-13","cited_by_count":1,"area":"wm"},{"id":"2607.27201","title":"Mental World Modeling","created":"2026-07-29","cited_by_count":1,"area":"wm"},{"id":"2608.26200","title":"GameWAM: A World Action Model for Video Games","created":"2026-08-25","cited_by_count":1,"area":"wm"},{"id":"2602.01644","title":"From Perception to Action: Spatial AI Agents and World Models","created":"2026-02-02","cited_by_count":0,"area":"wm"},{"id":"2602.14857","title":"World Models for Policy Refinement in StarCraft II","created":"2026-02-16","cited_by_count":0,"area":"wm"},{"id":"2605.02475","title":"Shadow-Loom: Causal Reasoning over Graphical World Models of Narratives","created":"2026-05-04","cited_by_count":0,"area":"wm"},{"id":"2606.19476","title":"Can In-Context Learning Support Intrinsic Curiosity?","created":"2026-06-17","cited_by_count":0,"area":"wm"},{"id":"2606.21315","title":"Social World Model for Lifelong Social Intelligence","created":"2026-06-19","cited_by_count":0,"area":"wm"},{"id":"2606.29495","title":"Cognitive World Model for Progressive BDI/E Trajectory Evaluation of Conversational Agents","created":"2026-06-28","cited_by_count":0,"area":"wm"},{"id":"2607.01767","title":"Repair the Amplifier, Not the Symptom: Stable World-Model Correction for Agent Rollouts","created":"2026-07-02","cited_by_count":0,"area":"wm"},{"id":"2607.08894","title":"GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning","created":"2026-07-09","cited_by_count":0,"area":"wm"},{"id":"2608.02713","title":"Quo Vadis, World Modeling?","created":"2026-08-03","cited_by_count":0,"area":"wm"},{"id":"2608.26788","title":"Decoupling Planning and Control for Instructable Agents","created":"2026-08-27","cited_by_count":0,"area":"wm"},{"id":"2609.13257","title":"Sampling headroom is not selection gain: a compute-value audit of test-time scaling for video world models","created":"2026-09-06","cited_by_count":0,"area":"wm"},{"id":"2609.31874","title":"COUNTERMEM: World-Model Verified Counter-Factual Memory for Language Agents","created":"2026-09-25","cited_by_count":0,"area":"wm"},{"id":"2609.32692","title":"World Agent: Can Language Models Keep a World Running?","created":"2026-09-26","cited_by_count":0,"area":"wm"},{"id":"2609.37810","title":"Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents","created":"2026-09-29","cited_by_count":0,"area":"wm"},{"id":"2609.38733","title":"Code to Control: Synthesizing Parameterized Reactive Controllers","created":"2026-09-30","cited_by_count":0,"area":"wm"},{"id":"2610.02331","title":"World Editing: Intervening on Executable Worlds at Increasing Depth","created":"2026-10-01","cited_by_count":0,"area":"wm"},{"id":"2610.10778","title":"MemoWM: How World Models Change What Agents Need to Remember","created":"2026-10-07","cited_by_count":0,"area":"wm"},{"id":"2610.12235","title":"Language Models as AI Research World Models","created":"2026-10-08","cited_by_count":0,"area":"wm"},{"id":"2610.12789","title":"EvoBelief: Falsifiable World Models for Self-Improving LLM Agents","created":"2026-10-08","cited_by_count":0,"area":"wm"},{"id":"2610.13912","title":"RSI-Anything: Unlocking Recursive Self-Improvement with World Models","created":"2026-10-09","cited_by_count":0,"area":"wm"},{"id":"2610.17114","title":"D-World: An Explicit World-Language-Action Model with Recursive Self-Improvement under Dual Control","created":"2026-10-12","cited_by_count":0,"area":"wm"},{"id":"2610.20240","title":"PAWA: Panoramic Action-conditioned World Modeling for Multiple Agents","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}