Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models
cs.AI
Submitted: 2026-05-16
Updated: 2026-11-04
Terminology
Sources
- Never Give Up: Learning Directed Exploration Strategies
- Exploration by Random Network Distillation
- Go-Explore: a New Approach for Hard-Exploration Problems
- Diversity is All You Need: Learning Skills without a Reward Function
- World Models
- Mastering Diverse Domains through World Models
- TD-MPC2: Scalable, Robust World Models for Continuous Control
- Code World Models for General Game Playing
- PoE-World: Compositional World Modeling with Products of Programmatic Experts
- From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents
- DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
- Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT
- Code over Words: Overcoming Semantic Inertia via Code-Grounded Reasoning
- WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
- PatchZero: Zero-Shot Automatic Patch Correctness Assessment
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents