# "Stop replacing salt with sugar!'': Towards Intuitive Human-Agent Teaching

arXiv: https://arxiv.org/abs/2509.24651 · HTML: https://mlsanity.com/paper/2509.24651/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [A Semantic Loss Function for Deep Learning with Symbolic Knowledge](https://mlsanity.com/paper/1711.11157/) (2017)
- [Neural-Symbolic Learning and Reasoning: A Survey and Interpretation](https://mlsanity.com/paper/1711.03902/) (2017)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images](https://mlsanity.com/paper/1810.06553/) (2018)
- [Learning from Few Examples: A Summary of Approaches to Few-Shot Learning](https://mlsanity.com/paper/2203.04291/) (2022)
- [A Survey on Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.08130/) (2023)
- [A Survey on Interactive Reinforcement Learning: Design Principles and Open Challenges](https://mlsanity.com/paper/2105.12949/) (2021)
- [Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases](https://mlsanity.com/paper/2102.11965/) (2021)
- [StarSpace: Embed All The Things!](https://mlsanity.com/paper/1709.03856/) (2017)
- [People infer recursive visual concepts from just a few examples](https://mlsanity.com/paper/1904.08034/) (2019)
- [Recent Research Advances on Interactive Machine Learning](https://mlsanity.com/paper/1811.04548/) (2018)
- [An Overview of Deep Learning Architectures in Few-Shot Learning Domain](https://mlsanity.com/paper/2008.06365/) (2020)
- [Learning to Substitute Ingredients in Recipes](https://mlsanity.com/paper/2302.07960/) (2023)
- [Establishing Shared Query Understanding in an Open Multi-Agent System](https://mlsanity.com/paper/2305.09349/) (2023)
- [Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniques](https://mlsanity.com/paper/2308.15899/) (2023)

## Abstract (arXiv)

Humans quickly learn new concepts from a small number of examples. Replicating this capacity with Artificial Intelligence (AI) systems has proven to be challenging. When it comes to learning subjective tasks-where there is an evident scarcity of data-this capacity needs to be recreated. In this work, we propose an intuitive human-agent teaching architecture in which the human can teach an agent how to perform a task by providing demonstrations, i.e., examples. To have an intuitive interaction, we argue that the agent should be able to learn incrementally from a few single examples. To allow for this, our objective is to broaden the agent's task understanding using domain knowledge. Then, using a learning method to enable the agent to learn efficiently from a limited number of examples. Finally, to optimize how human can select the most representative and less redundant examples to provide the agent with. We apply our proposed method to the subjective task of ingredient substitution, where the agent needs to learn how to substitute ingredients in recipes based on human examples. We replicate human input using the Recipe1MSubs dataset. In our experiments, the agent achieves half its task performance after only 100 examples are provided, compared to the complete training set of 50k examples. We show that by providing examples in strategic order along with a learning method that leverages external symbolic knowledge, the agent can generalize more efficiently.