Teach, Abstract, Apply: A Framework for Dialogue-Driven Task Learning with Collaborative Robots
cs.RO, cs.CL
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: Preprint
Code: https://github.com/agentskills/agentskills
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Collaborative robots (cobots) are designed to be safer and more interactive than traditional industrial robots, share the same workspace as humans…
Terminology
Abstract
Collaborative robots (cobots) are designed to be safer and more interactive than traditional industrial robots, share the same workspace as humans, and assist them in a range of shop-floor tasks such as palletization, joint assembly, and part inspection. Many of these tasks involve repetitive workflows that may evolve with changes in production environments and task specifications. These requirements motivate the need for intuitive interfaces that allow workers to modify workflows on the shop floor and generalise these routines for future use. This work introduces the Teach-Abstract-Apply (TAA) framework, which enables human operators to (a) teach new workflows to cobots in natural language, (b) abstract the taught workflows into skills for later use, and (c) apply these skills in different settings. As a case study, we apply the TAA framework to a collaborative structure-building task and evaluate it with both open-weight (Qwen3-Coder) and closed (GPT5.2-Codex) models in self-play and cross-model configurations. Our results show that skill abstraction improves task success rates and reduces interaction cost. Beyond automated evaluation, a preliminary human-in-the-loop study suggests that the pipeline also works with human instructions.
Sources
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- SimEX: Simulation-Integrated Robotics AutoResearch
- Robo-Instruct: Simulator-Augmented Instruction Alignment For Finetuning Code LLMs
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- Towards No-Code Programming of Cobots: Experiments with Code Synthesis by Large Code Models for Conversational Programming
- ASPIRE: Agentic /Skills Discovery for Robotics
- Machine Translation from Natural Language to Code using Long-Short Term Memory
- Large Language Models as Optimizers
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation