mlsanityData to 14 Oct 2026

InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning

arXiv 2405.19758 ↗First posted 30 May 2024cs.ROcited by 31

Not on the map. Why?

Abstract (arXiv)

Learning abstract state representations and knowledge is crucial for long-horizon robot planning. We present InterPreT, an LLM-powered framework for robots to learn symbolic predicates from language feedback of human non-experts during embodied interaction. The learned predicates provide relational abstractions of the environment state, facilitating the learning of symbolic operators that capture action preconditions and effects. By compiling the learned predicates and operators into a PDDL domain on-the-fly, InterPreT allows effective planning toward arbitrary in-domain goals using a PDDL planner. In both simulated and real-world robot manipulation domains, we demonstrate that InterPreT reliably uncovers the key predicates and operators governing the environment dynamics. Although learned from simple training tasks, these predicates and operators exhibit strong generalization to novel tasks with significantly higher complexity. In the most challenging generalization setting, InterPreT attains success rates of 73% in simulation and 40% in the real world, substantially outperforming baseline methods.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 May 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 10; 2025: 11; 2026: 10.

31 papers.

Sort:

By area:

  1. 2024VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planningcited by 39
  2. 2025LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Modelscited by 38
  3. 2024ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoningcited by 27
  4. 2024M2Diffuser: Diffusion-based Trajectory Optimization for Mobile Manipulation in 3D Scenescited by 27
  5. 2025Sotopia-RL: Reward Design for Social Intelligencecited by 24
  6. 2024Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Modelscited by 17
  7. 2024doScenes: An Autonomous Driving Dataset with Natural Language Instruction for Human Interaction and Vision-Language Navigationcited by 15
  8. 2025Learning Compositional Behaviors from Demonstration and Languagecited by 15
  9. 2024From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Modelscited by 11
  10. 2024Language Models can Infer Action Semantics for Symbolic Planners from Environment Feedbackcited by 8
  11. 2025Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPscited by 4
  12. 2025SLAP: Shortcut Learning for Abstract Planningcited by 3
19 more
  1. 2026Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperationcited by 3
  2. 2026Kintsugi: Learning Policies by Repairing Executable Knowledge Basescited by 3
  3. 2024CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Buildingcited by 2
  4. 2025Towards Fast, Memory-based and Data-Efficient Vision-Language Policycited by 2
  5. 2025Unifying Deep Predicate Invention with Pre-trained Foundation Modelscited by 2
  6. 2024Neuro-Symbolic Skill Discovery for Conditional Multi-Level Planningcited by 1
  7. 2025Learning Hierarchical Domain Models Through Environment-Grounded Interactioncited by 1
  8. 2025PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Modelscited by 1
  9. 2025RoboPilot: Generalizable Dynamic Robotic Manipulation with Dual-thinking Modescited by 1
  10. 2026Meanings and Measurements: Multi-Agent Probabilistic Grounding for Vision-Language Navigationcited by 1
  11. 2026StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillationcited by 1
  12. 2024Visual Error Patterns in Multi-Modal AI: A Statistical Approachcited by 0
  13. 2025Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structurescited by 0
  14. 2026Grounding Vision and Language to 3D Masks for Long-Horizon Box Rearrangementcited by 0
  15. 2026Learning Transferable Latent User Preferences for Human-Aligned Decision Makingcited by 0
  16. 2026Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planningcited by 0
  17. 2026Foresight: Iterative Reasoning About Clues that Matter for Navigationcited by 0
  18. 2026TANDEM: Task and Motion Planning with As-Needed Demonstrations for Efficient Vision-Language-Action Model Fine-tuningcited by 0
  19. 2026Bayesian Active Learning for Intent Disambiguation in Interactive Robot Planningcited by 0