# Infer Human's Intentions Before Following Natural Language Instructions

arXiv: https://arxiv.org/abs/2409.18073 · HTML: https://mlsanity.com/paper/2409.18073/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 26 Sep 2024.

## Builds on (most cited first, 18 of 18)

- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [TEACh: Task-driven Embodied Agents that Chat](https://mlsanity.com/paper/2110.00534/) (2021)
- [GreaseLM: Graph REASoning Enhanced Language Models for Question Answering](https://mlsanity.com/paper/2201.08860/) (2022)
- [Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration](https://mlsanity.com/paper/2010.09890/) (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)
- [DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following](https://mlsanity.com/paper/2202.13330/) (2022)
- [Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion](https://mlsanity.com/paper/2108.04927/) (2021)
- [Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems](https://mlsanity.com/paper/1811.00720/) (2018)
- [COMBO: Compositional World Models for Embodied Multi-Agent Cooperation](https://mlsanity.com/paper/2404.10775/) (2024)
- [Two Body Problem: Collaborative Visual Task Completion](https://mlsanity.com/paper/1904.05879/) (2019)
- [HandMeThat: Human-Robot Communication in Physical and Social Environments](https://mlsanity.com/paper/2310.03779/) (2023)
- [Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior](https://mlsanity.com/paper/2108.04812/) (2021)
- [GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment](https://mlsanity.com/paper/2403.11075/) (2024)

## Built on by (most cited first, 10 of 10)

- [Multi-agent Embodied AI: Advances and Future Directions](https://mlsanity.com/paper/2505.05108/) (2025)
- [Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning](https://mlsanity.com/paper/2504.17950/) (2025)
- [Modeling Others' Minds as Code](https://mlsanity.com/paper/2510.01272/) (2025)
- [Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language](https://mlsanity.com/paper/2511.14565/) (2025)
- [Neuro Symbolic Knowledge Reasoning for Procedural Video Question Answering](https://mlsanity.com/paper/2503.14957/) (2025)
- [Identifying, Evaluating, and Mitigating Risks of AI Thought Partnerships](https://mlsanity.com/paper/2505.16899/) (2025)
- [Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperation](https://mlsanity.com/paper/2602.19304/) (2026)
- [IntentVLM: Open-Vocabulary Intention Recognition through Forward-Inverse Modeling with Video-Language Models](https://mlsanity.com/paper/2604.24002/) (2026)
- [Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agents](https://mlsanity.com/paper/2608.27866/) (2026)
- [HelpMeOut: A Neuropsychology-Grounded Benchmark for Error-Aware Monitoring of Household Task Execution](https://mlsanity.com/paper/2610.17694/) (2026)

## Abstract (arXiv)

For AI agents to be helpful to humans, they should be able to follow natural language instructions to complete everyday cooperative tasks in human environments. However, real human instructions inherently possess ambiguity, because the human speakers assume sufficient prior knowledge about their hidden goals and intentions. Standard language grounding and planning methods fail to address such ambiguities because they do not model human internal goals as additional partially observable factors in the environment. We propose a new framework, Follow Instructions with Social and Embodied Reasoning (FISER), aiming for better natural language instruction following in collaborative embodied tasks. Our framework makes explicit inferences about human goals and intentions as intermediate reasoning steps. We implement a set of Transformer-based models and evaluate them over a challenging benchmark, HandMeThat. We empirically demonstrate that using social reasoning to explicitly infer human intentions before making action plans surpasses purely end-to-end approaches. We also compare our implementation with strong baselines, including Chain of Thought prompting on the largest available pre-trained language models, and find that FISER provides better performance on the embodied social reasoning tasks under investigation, reaching the state-of-the-art on HandMeThat.