# Learning adaptive planning representations with natural language guidance

arXiv: https://arxiv.org/abs/2312.08566 · HTML: https://mlsanity.com/paper/2312.08566/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 13 Dec 2023.

## Builds on (most cited first, 30 of 31)

- [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)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020)
- [Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory](https://mlsanity.com/paper/2305.17144/) (2023)
- [EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought](https://mlsanity.com/paper/2305.15021/) (2023)
- [Modular Multitask Reinforcement Learning with Policy Sketches](https://mlsanity.com/paper/1611.01796/) (2016)
- [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020)
- [A Survey of Reinforcement Learning Informed by Natural Language](https://mlsanity.com/paper/1906.03926/) (2019)
- [Generalized Planning in PDDL Domains with Pretrained Large Language Models](https://mlsanity.com/paper/2305.11014/) (2023)
- [Language as an Abstraction for Hierarchical Deep Reinforcement Learning](https://mlsanity.com/paper/1906.07343/) (2019)
- [Translating Natural Language to Planning Goals with Large-Language Models](https://mlsanity.com/paper/2302.05128/) (2023)
- [Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation](https://mlsanity.com/paper/2109.01115/) (2021)
- [Skill Induction and Planning with Latent Language](https://mlsanity.com/paper/2110.01517/) (2021)
- [Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling](https://mlsanity.com/paper/2301.12050/) (2023)
- [Mapping Instructions and Visual Observations to Actions with Reinforcement Learning](https://mlsanity.com/paper/1704.08795/) (2017)
- [Learning Symbolic Operators for Task and Motion Planning](https://mlsanity.com/paper/2103.00589/) (2021)
- [Top-Down Synthesis for Library Learning](https://mlsanity.com/paper/2211.16605/) (2022)
- [People construct simplified mental representations to plan](https://mlsanity.com/paper/2105.06948/) (2021)
- [Leveraging Language to Learn Program Abstractions and Search Heuristics](https://mlsanity.com/paper/2106.11053/) (2021)
- [Learning First-Order Symbolic Representations for Planning from the Structure of the State Space](https://mlsanity.com/paper/1909.05546/) (2019)
- [Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning](https://mlsanity.com/paper/2011.00517/) (2020)
- [Understanding the Power and Limitations of Teaching with Imperfect Knowledge](https://mlsanity.com/paper/2003.09712/) (2020)
- [babble: Learning Better Abstractions with E-Graphs and Anti-Unification](https://mlsanity.com/paper/2212.04596/) (2022)
- [Learning and Leveraging Verifiers to Improve Planning Capabilities of Pre-trained Language Models](https://mlsanity.com/paper/2305.17077/) (2023)

## Built on by (most cited first, 30 of 36)

- [Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems](https://mlsanity.com/paper/2405.06624/) (2024)
- [Combining Induction and Transduction for Abstract Reasoning](https://mlsanity.com/paper/2411.02272/) (2024)
- [Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo](https://mlsanity.com/paper/2504.13139/) (2025)
- [Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search](https://mlsanity.com/paper/2405.15383/) (2024)
- [Large Language Models for Planning: A Comprehensive and Systematic Survey](https://mlsanity.com/paper/2505.19683/) (2025)
- [ReGAL: Refactoring Programs to Discover Generalizable Abstractions](https://mlsanity.com/paper/2401.16467/) (2024)
- [WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents](https://mlsanity.com/paper/2410.07484/) (2024)
- [PoE-World: Compositional World Modeling with Products of Programmatic Experts](https://mlsanity.com/paper/2505.10819/) (2025)
- [Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors](https://mlsanity.com/paper/2402.04210/) (2024)
- [Empowering Large Language Model Agents through Action Learning](https://mlsanity.com/paper/2402.15809/) (2024)
- [Explaining Datasets in Words: Statistical Models with Natural Language Parameters](https://mlsanity.com/paper/2409.08466/) (2024)
- [On the Limit of Language Models as Planning Formalizers](https://mlsanity.com/paper/2412.09879/) (2024)
- [PROC2PDDL: Open-Domain Planning Representations from Texts](https://mlsanity.com/paper/2403.00092/) (2024)
- [Learning Compositional Behaviors from Demonstration and Language](https://mlsanity.com/paper/2505.21981/) (2025)
- [PDDLEGO: Iterative Planning in Textual Environments](https://mlsanity.com/paper/2405.19793/) (2024)
- [Synthesizing world models for bilevel planning](https://mlsanity.com/paper/2503.20124/) (2025)
- [Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models](https://mlsanity.com/paper/2507.12547/) (2025)
- [ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning](https://mlsanity.com/paper/2511.02424/) (2025)
- [LASP: Surveying the State-of-the-Art in Large Language Model-Assisted AI Planning](https://mlsanity.com/paper/2409.01806/) (2024)
- [REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?](https://mlsanity.com/paper/2505.10872/) (2025)
- [Modeling Others' Minds as Code](https://mlsanity.com/paper/2510.01272/) (2025)
- [WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents](https://mlsanity.com/paper/2504.15785/) (2025)
- [PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation](https://mlsanity.com/paper/2505.21652/) (2025)
- [Code-enabled language models can outperform reasoning models on diverse tasks](https://mlsanity.com/paper/2510.20909/) (2025)
- [Extracting and Following Paths for Robust Relational Reasoning with Large Language Models](https://mlsanity.com/paper/2412.17963/) (2024)
- [Language Model as Planner and Formalizer under Constraints](https://mlsanity.com/paper/2510.05486/) (2025)
- [Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents](https://mlsanity.com/paper/2602.00929/) (2026)
- [Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperation](https://mlsanity.com/paper/2602.19304/) (2026)
- [CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Building](https://mlsanity.com/paper/2410.13756/) (2024)
- [Iterative Formalization and Planning in Partially Observable Environments](https://mlsanity.com/paper/2505.13126/) (2025)

## Abstract (arXiv)

Effective planning in the real world requires not only world knowledge, but the ability to leverage that knowledge to build the right representation of the task at hand. Decades of hierarchical planning techniques have used domain-specific temporal action abstractions to support efficient and accurate planning, almost always relying on human priors and domain knowledge to decompose hard tasks into smaller subproblems appropriate for a goal or set of goals. This paper describes Ada (Action Domain Acquisition), a framework for automatically constructing task-specific planning representations using task-general background knowledge from language models (LMs). Starting with a general-purpose hierarchical planner and a low-level goal-conditioned policy, Ada interactively learns a library of planner-compatible high-level action abstractions and low-level controllers adapted to a particular domain of planning tasks. On two language-guided interactive planning benchmarks (Mini Minecraft and ALFRED Household Tasks), Ada strongly outperforms other approaches that use LMs for sequential decision-making, offering more accurate plans and better generalization to complex tasks.