mlsanityData to 14 Oct 2026

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

arXiv 2509.24651 ↗First posted 29 Sep 2025cs.AIcited by 0

Not on the map. Why?

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.

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

19 of 53 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 270
  6. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 196
  7. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  8. 2018Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Imagescited by 118
  9. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  10. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  11. 2021A Survey on Interactive Reinforcement Learning: Design Principles and Open Challengescited by 41
  12. 2021Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use casescited by 39
7 more
  1. 2017StarSpace: Embed All The Things!cited by 24
  2. 2019People infer recursive visual concepts from just a few examplescited by 23
  3. 2018Recent Research Advances on Interactive Machine Learningcited by 17
  4. 2020An Overview of Deep Learning Architectures in Few-Shot Learning Domaincited by 16
  5. 2023Learning to Substitute Ingredients in Recipescited by 8
  6. 2023Establishing Shared Query Understanding in an Open Multi-Agent Systemcited by 1
  7. 2023Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniquescited by 1

Built on by

Not cited yet.