cs.RONov 15, 2026

CRAFT: A Robot-Agent Harness with Scope-Aware Adaptation

Authors: Peng Zhang, Jiawen Wang, Cheng Xue, Jochen Renz

Organizations: Australian National University

Abstract

A robot may know how to move an object yet still need to learn where it belongs. When a person rejects a placement, the robot must decide whether the correction applies only to that situation or expresses a broader rule. We study this problem in CRAFT (Contextual Requirement Adaptation with Frozen Tools), a framework for learning local requirements without retraining robot skills. It records physical success separately from whether an action meets the requirement. Our scope ladder uses memory when an action has already been judged in a nearly identical situation. Elsewhere, it combines memory, explicit rules and a learner for requirements beyond those rules, weighting their predictions by how well they predicted earlier feedback. Controlled studies show gains over correction memory alone in utility, which rewards acceptable actions and charges for mistakes and questions. In camera-grounded robot simulations, the ladder asks fewer questions than language-model agents with persistent memory, but some of those agents take fewer wrong actions and succeed more often after requirements change. All execution failures and timeouts remain in the evaluation. These results support combining specific memories with broader rules, while leaving reliable adaptation to changing requirements unresolved. All evidence comes from simulation with generated requirements and simulated feedback.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LACE-CRAFT: Robot Co-Design with Actor Inheritance and Blackboard Collaboration

    Oct 7, 2026Yuhan Wen, Jiawei Wang, Qixuan Zhang +3Robot Morphology-Control Co-DesignRobot Policy Adaptation

  2. MIND: Instruction-Conditioned Incremental Grounding for Robots

    Oct 13, 2026Mohamed Abouagour, Junhyun Nam, Wonse Jo +1Incremental ComputationLanguage-Conditioned Robot Planning

  3. Lifelong Language-Conditioned Robotic Manipulation Learning

    Mar 5, 2026Xudong Wang, Zebin Han, Zhiyu Liu +5Language-Conditioned Robot ManipulationContinual Robot Learning