# LLM-BabyBench: Can Language Models Plan in Worlds They Can Simulate?

arXiv: https://arxiv.org/abs/2505.12135 · HTML: https://mlsanity.com/paper/2505.12135/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 38 of its 45 references that are in the map.
- First posted on arXiv 17 May 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 38)

- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Language Models Represent Space and Time](https://mlsanity.com/paper/2310.02207/) (2023)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning](https://mlsanity.com/paper/1810.08272/) (2018)
- [Benchmarking the Spectrum of Agent Capabilities](https://mlsanity.com/paper/2109.06780/) (2021)
- [The NetHack Learning Environment](https://mlsanity.com/paper/2006.13760/) (2020)
- [BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games](https://mlsanity.com/paper/2411.13543/) (2024)
- [Stream of Search (SoS): Learning to Search in Language](https://mlsanity.com/paper/2404.03683/) (2024)
- [Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making](https://mlsanity.com/paper/2410.07166/) (2024)
- [Does Prompt Formatting Have Any Impact on LLM Performance?](https://mlsanity.com/paper/2411.10541/) (2024)

## Built on by (most cited first, 2 of 2)

- [Meta-R1: Empowering Large Reasoning Models with Metacognition](https://mlsanity.com/paper/2508.17291/) (2025)
- [Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning](https://mlsanity.com/paper/2605.28277/) (2026)

## Abstract (arXiv)

Interactive benchmarks for LLMs usually report a single metric, even though succeeding in them requires models to show several different skills. While those benchmarks are useful for measuring the overall capability of models to perform the downstream task, it is harder to identify which skill was lacking and caused failure solely from the aggregate score. For example, in benchmarks where models are supposed to navigate a simulated world to perform a task, failures can come from perception, an ambiguous instruction, retrieval, missing commonsense about what actions do, unknown dynamics, or planning. benchmark recasts the procedurally generated BabyAI gridworld as a fully observable, purely textual environment designed to evaluate planning separately from those factors. The nature of the environment and the structure of the prompt control for the other factors cited above. To evaluate the models, we define the PPD suite: Predict asks for the state that follows an action sequence, Plan asks for an action sequence that reaches a goal, and Decompose asks for a subgoal sequence that achieves a mission. Across seven frontier and open models, queried zero-shot, we find simulation far ahead of planning for every model, close to saturated for the strongest. The length of the required solution governs planning failure, and each of the four strongest models has a horizon beyond which single-attempt success collapses. The responses of claude-opus-4-6 and claude-sonnet-4-6, which show their working step by step, reveal that they plan by proposing L-shaped corridors, which is consistent with their successful plans staying near-optimal while success falls. At the subgoal level, decomposition precision likewise falls to zero on long missions, while comprehension of those missions persists.