Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents
cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Grounding LLMs For Robot Task Planning Using Closed-loop State Feedback
- TextWorld: A Learning Environment for Text-based Games
- "No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy
- Inner Monologue: Embodied Reasoning through Planning with Language Models
- Interactive Robot Learning from Verbal Correction
- Correcting Robot Plans with Natural Language Feedback
- Yell At Your Robot: Improving On-the-Fly from Language Corrections
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems