mlsanityData to 14 Oct 2026

Learning adaptive planning representations with natural language guidance

arXiv 2312.08566 ↗First posted 13 Dec 2023cs.AI cs.CL cs.ROcited by 36

Not on the map. Why?

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.

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

31 of 50 references.

References · 31

  1. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  2. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  3. 2017Hindsight Experience Replaycited by 1,136
  4. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  5. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 783
  6. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 501
  7. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
  8. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 398
  9. 2020Integrated Task and Motion Planningcited by 290
  10. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 289
  11. 2023EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thoughtcited by 279
  12. 2016Modular Multitask Reinforcement Learning with Policy Sketchescited by 203
19 more
  1. 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 161
  2. 2019A Survey of Reinforcement Learning Informed by Natural Languagecited by 154
  3. 2023Generalized Planning in PDDL Domains with Pretrained Large Language Modelscited by 139
  4. 2019Language as an Abstraction for Hierarchical Deep Reinforcement Learningcited by 138
  5. 2023Translating Natural Language to Planning Goals with Large-Language Modelscited by 133
  6. 2021Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotationcited by 118
  7. 2021Skill Induction and Planning with Latent Languagecited by 99
  8. 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modellingcited by 88
  9. 2017Mapping Instructions and Visual Observations to Actions with Reinforcement Learningcited by 81
  10. 2021Learning Symbolic Operators for Task and Motion Planningcited by 58
  11. 2022Top-Down Synthesis for Library Learningcited by 58
  12. 2021People construct simplified mental representations to plancited by 47
  13. 2021Leveraging Language to Learn Program Abstractions and Search Heuristicscited by 45
  14. 2019Learning First-Order Symbolic Representations for Planning from the Structure of the State Spacecited by 38
  15. 2020Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learningcited by 32
  16. 2020Understanding the Power and Limitations of Teaching with Imperfect Knowledgecited by 23
  17. 2022babble: Learning Better Abstractions with E-Graphs and Anti-Unificationcited by 23
  18. 2023Learning and Leveraging Verifiers to Improve Planning Capabilities of Pre-trained Language Modelscited by 10
  19. 2023Learning Rational Subgoals from Demonstrations and Instructionscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 14; 2025: 16; 2026: 6.

36 papers.

Sort:

By area:

  1. 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systemscited by 96
  2. 2024Combining Induction and Transduction for Abstract Reasoningcited by 53
  3. 2025Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlocited by 46
  4. 2024Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Searchcited by 40
  5. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 40
  6. 2024ReGAL: Refactoring Programs to Discover Generalizable Abstractionscited by 36
  7. 2024WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agentscited by 26
  8. 2025PoE-World: Compositional World Modeling with Products of Programmatic Expertscited by 26
  9. 2024Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviorscited by 25
  10. 2024Empowering Large Language Model Agents through Action Learningcited by 22
  11. 2024Explaining Datasets in Words: Statistical Models with Natural Language Parameterscited by 21
  12. 2024On the Limit of Language Models as Planning Formalizerscited by 18
24 more
  1. 2024PROC2PDDL: Open-Domain Planning Representations from Textscited by 15
  2. 2025Learning Compositional Behaviors from Demonstration and Languagecited by 15
  3. 2024PDDLEGO: Iterative Planning in Textual Environmentscited by 14
  4. 2025Synthesizing world models for bilevel planningcited by 14
  5. 2025Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Modelscited by 14
  6. 2025ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planningcited by 12
  7. 2024LASP: Surveying the State-of-the-Art in Large Language Model-Assisted AI Planningcited by 9
  8. 2025REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?cited by 7
  9. 2025Modeling Others' Minds as Codecited by 7
  10. 2025WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agentscited by 5
  11. 2025PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulationcited by 4
  12. 2025Code-enabled language models can outperform reasoning models on diverse taskscited by 4
  13. 2024Extracting and Following Paths for Robust Relational Reasoning with Large Language Modelscited by 3
  14. 2025Language Model as Planner and Formalizer under Constraintscited by 3
  15. 2026Learning Abstractions for Hierarchical Planning in Program-Synthesis Agentscited by 3
  16. 2026Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperationcited by 3
  17. 2024CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Buildingcited by 2
  18. 2025Iterative Formalization and Planning in Partially Observable Environmentscited by 1
  19. 2025Learning Hierarchical Domain Models Through Environment-Grounded Interactioncited by 1
  20. 2025PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Modelscited by 1
  21. 2026Joint Learning of Hierarchical Neural Options and Abstract World Modelcited by 1
  22. 2026Rollout Cards: A Reproducibility Standard for Agent Researchcited by 1
  23. 2026Robust Asynchronous Planning via Auto-Formalizationcited by 0
  24. 2026SCOPE: Evolving Symbolic World for Planning in Open-Ended Environmentscited by 0