Teach, Abstract, Apply: A Framework for Dialogue-Driven Task Learning with Collaborative Robots
Overview
This work presents the Teach-Abstract-Apply (TAA) framework, enabling human operators to teach collaborative robots new workflows via natural language, abstract these into reusable skills, and apply them across different settings. Evaluated on a structure-building task using both open-weight (Qwen3-Coder) and closed (GPT5.2-Codex) models in self-play and cross-model setups, the framework demonstrates that skill abstraction improves task success rates and reduces interaction costs. Preliminary human-in-the-loop testing indicates compatibility with human instructions.
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalTeach, Abstract, Apply: A Framework for Dialogue-Driven Task Learning with Collaborative Robots
This work presents the Teach-Abstract-Apply (TAA) framework, enabling human operators to teach collaborative robots new workflows via natural language, abstract these into reusable skills, and apply them across different settings. Evaluated on a structure-building task using both open-weight (Qwen3-Coder) and closed (GPT5.2-Codex) models in self-play and cross-model setups, the framework demonstrates that skill abstraction improves task success rates and reduces interaction costs. Preliminary human-in-the-loop testing indicates compatibility with human instructions.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).