Understanding Rollout Error in Graph World Models
cs.AI
Submitted: 2026-06-26
Updated: 2026-10-12
Code: https://github.com/Hik289/graph_
Terminology
Sources
- VRAG: Learning World Models for Interactive Video Generation
- World Models
- Learning Latent Dynamics for Planning from Pixels
- Mastering Diverse Domains through World Models
- Audited Skill-Graph Self-Improvement for Agentic LLMs via Verifiable Rewards, Experience Synthesis, and Continual Memory
- CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution
- Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems
- SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments
- Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism
- NeuralOS: Towards Simulating Operating Systems via Neural Generative Models
- Temporal Graph Networks for Deep Learning on Dynamic Graphs
- The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited
- Reinforcement Learning for Self-Improving Agent with Skill Library
- Dyn-O: Building Structured World Models with Object-Centric Representations
- iVideoGPT: Interactive VideoGPTs are Scalable World Models
- GraSP: Graph-Structured Skill Compositions for LLM Agents
- PIORF: Physics-Informed Ollivier-Ricci Flow for Long-Range Interactions in Mesh Graph Neural Networks
- Hierarchical Planning with Latent World Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems