# Few-shot Subgoal Planning with Language Models

arXiv: https://arxiv.org/abs/2205.14288 · HTML: https://mlsanity.com/paper/2205.14288/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 39 references that are in the map.
- First posted on arXiv 28 May 2022.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Implicit Representations of Meaning in Neural Language Models](https://mlsanity.com/paper/2106.00737/) (2021)
- [Interactive Fiction Games: A Colossal Adventure](https://mlsanity.com/paper/1909.05398/) (2019)
- [Noisy Channel Language Model Prompting for Few-Shot Text Classification](https://mlsanity.com/paper/2108.04106/) (2021)
- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [A Survey of Reinforcement Learning Informed by Natural Language](https://mlsanity.com/paper/1906.03926/) (2019)
- [Improving Text-to-SQL Evaluation Methodology](https://mlsanity.com/paper/1806.09029/) (2018)
- [FILM: Following Instructions in Language with Modular Methods](https://mlsanity.com/paper/2110.07342/) (2021)
- [Keep CALM and Explore: Language Models for Action Generation in Text-based Games](https://mlsanity.com/paper/2010.02903/) (2020)
- [Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures](https://mlsanity.com/paper/2007.08970/) (2020)
- [A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution](https://mlsanity.com/paper/2107.05612/) (2021)
- [Executing Instructions in Situated Collaborative Interactions](https://mlsanity.com/paper/1910.03655/) (2019)
- [Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion](https://mlsanity.com/paper/2108.04927/) (2021)
- [Unified Pragmatic Models for Generating and Following Instructions](https://mlsanity.com/paper/1711.04987/) (2017)
- [Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations](https://mlsanity.com/paper/2104.07478/) (2021)
- [Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring](https://mlsanity.com/paper/2106.03427/) (2021)
- [Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences](https://mlsanity.com/paper/1506.04089/) (2015)
- [Learning to Win by Reading Manuals in a Monte-Carlo Framework](https://mlsanity.com/paper/1401.5390/) (2014)
- [Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions](https://mlsanity.com/paper/2009.14259/) (2020)
- [Mutual Information and Diverse Decoding Improve Neural Machine Translation](https://mlsanity.com/paper/1601.00372/) (2016)

## Built on by (most cited first, 22 of 22)

- [AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents](https://mlsanity.com/paper/2403.08978/) (2024)
- [Agent Planning with World Knowledge Model](https://mlsanity.com/paper/2405.14205/) (2024)
- [Tree-Planner: Efficient Close-loop Task Planning with Large Language Models](https://mlsanity.com/paper/2310.08582/) (2023)
- [MPO: Boosting LLM Agents with Meta Plan Optimization](https://mlsanity.com/paper/2503.02682/) (2025)
- [BAGEL: Bootstrapping Agents by Guiding Exploration with Language](https://mlsanity.com/paper/2403.08140/) (2024)
- [An In-depth Survey of Large Language Model-based Artificial Intelligence Agents](https://mlsanity.com/paper/2309.14365/) (2023)
- [EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents](https://mlsanity.com/paper/2410.22662/) (2024)
- [Exploiting Language Models as a Source of Knowledge for Cognitive Agents](https://mlsanity.com/paper/2310.06846/) (2023)
- [Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents](https://mlsanity.com/paper/2410.22552/) (2024)
- [A Framework for Neurosymbolic Robot Action Planning using Large Language Models](https://mlsanity.com/paper/2303.00438/) (2023)
- [Integrating Diverse Knowledge Sources for Online One-shot Learning of Novel Tasks](https://mlsanity.com/paper/2208.09554/) (2022)
- [Improving Language Model Prompting in Support of Semi-autonomous Task Learning](https://mlsanity.com/paper/2209.07636/) (2022)
- [Unsupervised Task Graph Generation from Instructional Video Transcripts](https://mlsanity.com/paper/2302.09173/) (2023)
- [A Picture is Worth a Thousand Words: Language Models Plan from Pixels](https://mlsanity.com/paper/2303.09031/) (2023)
- [Code Models are Zero-shot Precondition Reasoners](https://mlsanity.com/paper/2311.09601/) (2023)
- [LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble](https://mlsanity.com/paper/2411.17135/) (2024)
- [Test-Time Alignment for Large Language Models via Textual Model Predictive Control](https://mlsanity.com/paper/2502.20795/) (2025)
- [Multimodal Contextualized Plan Prediction for Embodied Task Completion](https://mlsanity.com/paper/2305.06485/) (2023)
- [Improving Knowledge Extraction from LLMs for Task Learning through Agent Analysis](https://mlsanity.com/paper/2306.06770/) (2023)
- [MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems](https://mlsanity.com/paper/2504.17070/) (2025)
- [Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments](https://mlsanity.com/paper/2408.01024/) (2024)
- [STO-RL: Offline RL under Sparse Rewards via LLM-Guided Subgoal Temporal Order](https://mlsanity.com/paper/2601.08107/) (2026)

## 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.