ConEQsA: Concurrent and Asynchronous Embodied Questions Scheduling and Answering

Researchers introduce ConEQsA, an AI framework that enables embodied agents to handle multiple questions simultaneously in 3D environments with urgency-aware scheduling. The system uses shared memory to reduce redundant exploration and includes a new benchmark with 200 questions across 40 indoor scenes.

• →ConEQsA framework enables AI agents to handle multiple concurrent questions in 3D environments rather than processing them sequentially.
• →The system uses urgency-aware scheduling and shared group memory to improve efficiency and reduce redundant exploration.
• →Researchers created the CAEQs benchmark with 200 questions across 40 indoor scenes to evaluate concurrent embodied question answering.
• →New evaluation metrics DAR and NUWL were introduced to fairly assess multi-question AI agent performance.
• →Empirical results show ConEQsA consistently outperforms sequential baseline approaches in handling realistic workloads.