mlsanityData to 7 Oct 2026

Few-shot Subgoal Planning with Language Models

arXiv 2205.14288 ↗First posted 28 May 2022cs.CLcited by 22

Not on the map. Why?

Abstract (arXiv)

Pre-trained large language models have shown successful progress in many language understanding benchmarks. This work explores the capability of these models to predict actionable plans in real-world environments. Given a text instruction, we show that language priors encoded in pre-trained language models allow us to infer fine-grained subgoal sequences. In contrast to recent methods which make strong assumptions about subgoal supervision, our experiments show that language models can infer detailed subgoal sequences from few training sequences without any fine-tuning. We further propose a simple strategy to re-rank language model predictions based on interaction and feedback from the environment. Combined with pre-trained navigation and visual reasoning components, our approach demonstrates competitive performance on subgoal prediction and task completion in the ALFRED benchmark compared to prior methods that assume more subgoal supervision.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 32 of its 39 references that are in the map. First posted on arXiv 28 May 2022.

Builds on

32 of 39 references.

References · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  6. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  7. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  8. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  9. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
  10. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  11. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  12. 2021Implicit Representations of Meaning in Neural Language Modelscited by 179
20 more
  1. 2019Interactive Fiction Games: A Colossal Adventurecited by 165
  2. 2021Noisy Channel Language Model Prompting for Few-Shot Text Classificationcited by 163
  3. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  4. 2019A Survey of Reinforcement Learning Informed by Natural Languagecited by 154
  5. 2018Improving Text-to-SQL Evaluation Methodologycited by 133
  6. 2021FILM: Following Instructions in Language with Modular Methodscited by 119
  7. 2020Keep CALM and Explore: Language Models for Action Generation in Text-based Gamescited by 108
  8. 2020Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architecturescited by 95
  9. 2021A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Executioncited by 91
  10. 2019Executing Instructions in Situated Collaborative Interactionscited by 68
  11. 2021Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completioncited by 57
  12. 2017Unified Pragmatic Models for Generating and Following Instructionscited by 55
  13. 2021Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representationscited by 55
  14. 2021Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoringcited by 53
  15. 2015Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequencescited by 50
  16. 2014Learning to Win by Reading Manuals in a Monte-Carlo Frameworkcited by 39
  17. 2020Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructionscited by 36
  18. 2016Mutual Information and Diverse Decoding Improve Neural Machine Translationcited by 35
  19. 2021Language Models are Few-Shot Butlerscited by 27
  20. 2019Enabling Robots to Understand Incomplete Natural Language Instructions Using Commonsense Reasoningcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 9; 2024: 7; 2025: 3; 2026: 1.

22 papers.

Sort:

By area:

  1. 2024AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agentscited by 69
  2. 2024Agent Planning with World Knowledge Modelcited by 66
  3. 2023Tree-Planner: Efficient Close-loop Task Planning with Large Language Modelscited by 48
  4. 2025MPO: Boosting LLM Agents with Meta Plan Optimizationcited by 36
  5. 2024BAGEL: Bootstrapping Agents by Guiding Exploration with Languagecited by 34
  6. 2023An In-depth Survey of Large Language Model-based Artificial Intelligence Agentscited by 30
  7. 2024EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agentscited by 24
  8. 2023Exploiting Language Models as a Source of Knowledge for Cognitive Agentscited by 15
  9. 2024Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agentscited by 13
  10. 2023A Framework for Neurosymbolic Robot Action Planning using Large Language Modelscited by 11
  11. 2022Integrating Diverse Knowledge Sources for Online One-shot Learning of Novel Taskscited by 6
  12. 2022Improving Language Model Prompting in Support of Semi-autonomous Task Learningcited by 6
10 more
  1. 2023Unsupervised Task Graph Generation from Instructional Video Transcriptscited by 6
  2. 2023A Picture is Worth a Thousand Words: Language Models Plan from Pixelscited by 6
  3. 2023Code Models are Zero-shot Precondition Reasonerscited by 3
  4. 2024LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemblecited by 3
  5. 2025Test-Time Alignment for Large Language Models via Textual Model Predictive Controlcited by 2
  6. 2023Multimodal Contextualized Plan Prediction for Embodied Task Completioncited by 1
  7. 2023Improving Knowledge Extraction from LLMs for Task Learning through Agent Analysiscited by 1
  8. 2024Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environmentscited by 0
  9. 2025MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systemscited by 0
  10. 2026STO-RL: Offline RL under Sparse Rewards via LLM-Guided Subgoal Temporal Ordercited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025On the Limits of Innate Planning in Large Language Models
  2. 2026Latent Goal Prediction from Language for Model-Based Planning
  3. 2024Sub-goal Distillation: A Method to Improve Small Language Agents
  4. 2024Exploring and Benchmarking the Planning Capabilities of Large Language Models
  5. 2026A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners
  6. 2023Learning and Leveraging Verifiers to Improve Planning Capabilities of Pre-trained Language Models
  7. 2025Planning with Reasoning using Vision Language World Model
  8. 2023Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents