# Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models

arXiv: https://arxiv.org/abs/2605.16725 · HTML: https://mlsanity.com/paper/2605.16725/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 16 May 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 17 of 17)

- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Go-Explore: a New Approach for Hard-Exploration Problems](https://mlsanity.com/paper/1901.10995/) (2019)
- [Never Give Up: Learning Directed Exploration Strategies](https://mlsanity.com/paper/2002.06038/) (2020)
- [ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization](https://mlsanity.com/paper/2509.13313/) (2025)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [PoE-World: Compositional World Modeling with Products of Programmatic Experts](https://mlsanity.com/paper/2505.10819/) (2025)
- [Code World Models for General Game Playing](https://mlsanity.com/paper/2510.04542/) (2025)
- [DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards](https://mlsanity.com/paper/2304.10770/) (2023)
- [WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents](https://mlsanity.com/paper/2504.15785/) (2025)
- [From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents](https://mlsanity.com/paper/2602.04326/) (2026)
- [PatchZero: Zero-Shot Automatic Patch Correctness Assessment](https://mlsanity.com/paper/2303.00202/) (2023)
- [Code over Words: Overcoming Semantic Inertia via Code-Grounded Reasoning](https://mlsanity.com/paper/2601.18352/) (2026)

## Built on by (most cited first, 1 of 1)

- [Schema: Discovering Unknown Environments via Agentic Program Induction](https://mlsanity.com/paper/2609.39140/) (2026)

## Abstract (arXiv)

Executable world models can be read, edited, executed, and reused for planning, but only if the program captures the environment's transition law rather than semantic shortcuts in its surface vocabulary. We study online executable world-model learning under prior misalignment, where an agent must induce state-dependent dynamics from interaction evidence alone, without rule descriptions, reward signals, or trustworthy lexical priors. We introduce Alice, a closed-loop system that treats failed candidate updates as structural signal: when a candidate explains a new transition but loses previously explained ones, the preservation conflict reveals dynamics that the current program had conflated. Alice refines these conflicts into hypothesis classes that both provide compact, class-stratified preservation counterexamples for update and guide frontier exploration toward transitions that are novel and underrepresented with respect to the current program. We evaluate Alice on Baba in Wonderland, a prior-misaligned variant of Baba Is You that preserves simulator dynamics while replacing semantically meaningful rule-property labels with unrelated words. Experiments show that Alice substantially improves executable world-model learning under prior misalignment, and ablations show that both class refinement and class-aware exploration contribute.