{"total":107,"rows":[{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166,"area":"wm"},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2507.02825","title":"Establishing Best Practices for Building Rigorous Agentic Benchmarks","created":"2025-07-03","cited_by_count":102,"area":"agents"},{"id":"2405.06624","title":"Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems","created":"2024-05-10","cited_by_count":96,"area":"wm"},{"id":"2503.23350","title":"A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models","created":"2025-03-30","cited_by_count":87,"area":"agents"},{"id":"2501.03936","title":"PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides","created":"2025-01-07","cited_by_count":86,"area":null},{"id":"2602.10090","title":"Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning","created":"2026-02-10","cited_by_count":66,"area":"wm"},{"id":"2601.05808","title":"EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis","created":"2026-01-09","cited_by_count":63,"area":"agents"},{"id":"2411.02272","title":"Combining Induction and Transduction for Abstract Reasoning","created":"2024-11-04","cited_by_count":53,"area":"lr"},{"id":"2406.06485","title":"Can Language Models Serve as Text-Based World Simulators?","created":"2024-06-10","cited_by_count":52,"area":null},{"id":"2405.17503","title":"Code Repair with LLMs gives an Exploration-Exploitation Tradeoff","created":"2024-05-26","cited_by_count":51,"area":null},{"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":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2410.23156","title":"VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning","created":"2024-10-30","cited_by_count":39,"area":"wm"},{"id":"2509.02722","title":"Planning with Reasoning using Vision Language World Model","created":"2025-09-02","cited_by_count":36,"area":"wm"},{"id":"2411.08027","title":"LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Engines","created":"2024-11-12","cited_by_count":30,"area":"lr"},{"id":"2410.07484","title":"WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents","created":"2024-10-09","cited_by_count":26,"area":"wm"},{"id":"2502.13092","title":"Text2World: Benchmarking Large Language Models for Symbolic World Model Generation","created":"2025-02-18","cited_by_count":26,"area":"wm"},{"id":"2505.10819","title":"PoE-World: Compositional World Modeling with Products of Programmatic Experts","created":"2025-05-16","cited_by_count":26,"area":"wm"},{"id":"2510.04542","title":"Code World Models for General Game Playing","created":"2025-10-06","cited_by_count":26,"area":"wm"},{"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,"area":"agents"},{"id":"2605.06716","title":"From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms","created":"2026-05-07","cited_by_count":21,"area":"agents"},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2602.23008","title":"Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization","created":"2026-02-26","cited_by_count":19,"area":"agents"},{"id":"2412.09879","title":"On the Limit of Language Models as Planning Formalizers","created":"2024-12-13","cited_by_count":18,"area":null},{"id":"2501.03151","title":"Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches","created":"2025-01-06","cited_by_count":18,"area":"mllm"},{"id":"2405.13242","title":"Goals as Reward-Producing Programs","created":"2024-05-21","cited_by_count":14,"area":null},{"id":"2503.20124","title":"Synthesizing world models for bilevel planning","created":"2025-03-26","cited_by_count":14,"area":"wm"},{"id":"2507.12547","title":"Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models","created":"2025-07-16","cited_by_count":14,"area":null},{"id":"2508.10874","title":"SSRL: Self-Search Reinforcement Learning","created":"2025-08-14","cited_by_count":14,"area":"lr"},{"id":"2605.05138","title":"Executable World Models for ARC-AGI-3 in the Era of Coding Agents","created":"2026-05-06","cited_by_count":14,"area":"wm"},{"id":"2608.25927","title":"Code World Model: Coding Agent as World Brain","created":"2026-08-26","cited_by_count":14,"area":"wm"},{"id":"2608.27549","title":"Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning","created":"2026-08-27","cited_by_count":14,"area":"lr"},{"id":"2405.16450","title":"Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search","created":"2024-05-26","cited_by_count":13,"area":null},{"id":"2506.10341","title":"Formalizing Learning from Language Feedback with Provable Guarantees","created":"2025-06-12","cited_by_count":13,"area":null},{"id":"2511.09586","title":"Environment Scaling for Interactive Agentic Experience Collection: A Survey","created":"2025-11-12","cited_by_count":13,"area":"agents"},{"id":"2502.04728","title":"Generating Symbolic World Models via Test-time Scaling of Large Language Models","created":"2025-02-07","cited_by_count":12,"area":"wm"},{"id":"2505.02216","title":"LLM-Guided Probabilistic Program Induction for POMDP Model Estimation","created":"2025-05-04","cited_by_count":12,"area":null},{"id":"2506.06725","title":"WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making","created":"2025-06-07","cited_by_count":12,"area":"wm"},{"id":"2508.20134","title":"QAgent: An LLM-based Multi-Agent System for Autonomous OpenQASM programming","created":"2025-08-26","cited_by_count":11,"area":"agents"},{"id":"2502.16690","title":"From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task","created":"2025-02-23","cited_by_count":10,"area":"agents"},{"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":"2511.00162","title":"ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus","created":"2025-10-31","cited_by_count":10,"area":null},{"id":"2411.13410","title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback","created":"2024-11-20","cited_by_count":9,"area":null},{"id":"2512.22336","title":"Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback","created":"2025-12-26","cited_by_count":9,"area":"wm"},{"id":"2407.05700","title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct","created":"2024-07-08","cited_by_count":8,"area":"synth"},{"id":"2506.09272","title":"G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2510.01272","title":"Modeling Others' Minds as Code","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2605.30880","title":"PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments","created":"2026-05-29","cited_by_count":7,"area":"wm"},{"id":"2412.04057","title":"From Code to Play: Benchmarking Program Search for Games Using Large Language Models","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2503.13992","title":"The KoLMogorov Test: Compression by Code Generation","created":"2025-03-18","cited_by_count":5,"area":null},{"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":"2506.09656","title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","created":"2025-06-11","cited_by_count":5,"area":"agents"},{"id":"2601.13247","title":"Aligning Agentic World Models via Knowledgeable Experience Learning","created":"2026-01-19","cited_by_count":5,"area":"wm"},{"id":"2602.07672","title":"Debugging code world models","created":"2026-02-07","cited_by_count":5,"area":"wm"},{"id":"2507.22281","title":"CoEx -- Co-evolving World-model and Exploration","created":"2025-07-29","cited_by_count":4,"area":"wm"},{"id":"2509.17393","title":"Program Synthesis via Test-Time Transduction","created":"2025-09-22","cited_by_count":4,"area":null},{"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":"2510.05486","title":"Language Model as Planner and Formalizer under Constraints","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2602.00929","title":"Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents","created":"2026-01-31","cited_by_count":3,"area":"agents"},{"id":"2605.14175","title":"Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2607.15439","title":"Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?","created":"2026-07-16","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":"2501.16546","title":"Sample-Efficient Behavior Cloning Using General Domain Knowledge","created":"2025-01-27","cited_by_count":2,"area":"offlinerl"},{"id":"2503.08738","title":"Shedding Light in Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2504.20628","title":"Cognitive maps are generative programs","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2505.16422","title":"Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach","created":"2025-05-22","cited_by_count":2,"area":"wm"},{"id":"2506.14373","title":"Discrete JEPA: Learning Discrete Token Representations without Reconstruction","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2509.06736","title":"VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2509.24116","title":"Dual-Scale World Models for LLM Agents Towards Hard-Exploration Problems","created":"2025-09-28","cited_by_count":2,"area":"wm"},{"id":"2505.13126","title":"Iterative Formalization and Planning in Partially Observable Environments","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2509.00074","title":"Language and Experience: A Computational Model of Social Learning in Complex Tasks","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2511.15830","title":"Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions","created":"2025-11-19","cited_by_count":1,"area":null},{"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":"2602.03974","title":"Active Epistemic Control for Query-Efficient Verified Planning","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.28386","title":"COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2604.09604","title":"LLMs for Text-Based Exploration and Navigation Under Partial Observability","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2609.02322","title":"What Is Worth Representing? Representational Empowerment for Continual Model Construction","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2609.09163","title":"World-Time Compute with Verified Code World Models","created":"2026-07-07","cited_by_count":1,"area":"wm"},{"id":"2609.35047","title":"EMPIRIC: Experiment-Driven Learning of Residual World Models for Robot Planning","created":"2026-09-28","cited_by_count":1,"area":"wm"},{"id":"2609.35432","title":"Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence","created":"2026-09-28","cited_by_count":1,"area":"vla"},{"id":"2505.14948","title":"Programmatic Video Prediction Using Large Language Models","created":"2025-05-20","cited_by_count":0,"area":"wm"},{"id":"2510.03771","title":"OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation","created":"2025-10-04","cited_by_count":0,"area":"agents"},{"id":"2510.14825","title":"Programmatic Representation Learning with Language Models","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2602.10009","title":"Discovering High Level Patterns from Simulation Traces","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.13363","title":"Assessing Spear-Phishing Website Generation in Large Language Model Coding Agents","created":"2026-02-13","cited_by_count":0,"area":"agents"},{"id":"2603.18495","title":"Cross-Domain Demo-to-Code via Neurosymbolic Counterfactual Reasoning","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2605.24528","title":"Hypothesis Generation and Inductive Inference in Children and Language Models","created":"2026-05-23","cited_by_count":0,"area":"agents"},{"id":"2606.26094","title":"RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.27806","title":"Agent vs. Parametric World Models: Hybrid Planning for Reliable Language Agents","created":"2026-06-26","cited_by_count":0,"area":"wm"},{"id":"2607.02846","title":"Object-Centric Environment Modeling for Agentic Tasks","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2608.02713","title":"Quo Vadis, World Modeling?","created":"2026-08-03","cited_by_count":0,"area":"wm"},{"id":"2609.26458","title":"Code Plans, Diffusion Renders: Open-Ended Generative World Modeling","created":"2026-09-22","cited_by_count":0,"area":"wm"},{"id":"2609.35738","title":"Harness Learning Enables Generalizable Test-Time Adaptation","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.39140","title":"Schema: Discovering Unknown Environments via Agentic Program Induction","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.01215","title":"AutoGUIWorld: Image Generators as Visual World Models for GUI Agent","created":"2026-10-01","cited_by_count":0,"area":"wm"},{"id":"2610.01415","title":"Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.02331","title":"World Editing: Intervening on Executable Worlds at Increasing Depth","created":"2026-10-01","cited_by_count":0,"area":"wm"},{"id":"2610.02451","title":"A Simulation-Grounded Agentic VLM Framework for Wildfire Monitoring and Reporting","created":"2026-10-01","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}