[2509.11663] ConEQsA: Concurrent and Asynchronous Embodied Questions Scheduling and Answering

[2509.11663] ConEQsA: Concurrent and Asynchronous Embodied Questions Scheduling and Answering

arXiv - AI 4 min read

About this article

Abstract page for arXiv paper 2509.11663: ConEQsA: Concurrent and Asynchronous Embodied Questions Scheduling and Answering

Computer Science > Robotics arXiv:2509.11663 (cs) [Submitted on 15 Sep 2025 (v1), last revised 3 Mar 2026 (this version, v2)] Title:ConEQsA: Concurrent and Asynchronous Embodied Questions Scheduling and Answering Authors:Haisheng Wang, Dong Liu, Weiming Zhi View a PDF of the paper titled ConEQsA: Concurrent and Asynchronous Embodied Questions Scheduling and Answering, by Haisheng Wang and 2 other authors View PDF HTML (experimental) Abstract:This paper formulates the Embodied Questions Answering (EQsA) problem, introduces a corresponding benchmark, and proposes an agentic system to tackle the problem. Classical Embodied Question Answering (EQA) is typically formulated as answering one single question by actively exploring a 3D environment. Real deployments, however, often demand handling multiple questions that may arrive asynchronously and carry different urgencies. We formalize this setting as Embodied Questions Answering (EQsA) and present ConEQsA, an agentic framework for concurrent, urgency-aware scheduling and answering. ConEQsA leverages shared group memory to reduce redundant exploration, and a priority-planning method to dynamically schedule questions. To evaluate the EQsA setting fairly, we contribute the Concurrent Asynchronous Embodied Questions (CAEQs) benchmark containing 40 indoor scenes and five questions per scene (200 in total), featuring asynchronous follow-up questions and human-annotated urgency labels. We further propose metrics for EQsA performance: ...

Originally published on March 04, 2026. Curated by AI News.

Related Articles

UMKC Announces New Master of Science in Artificial Intelligence
Ai Infrastructure

UMKC Announces New Master of Science in Artificial Intelligence

UMKC announces a new Master of Science in Artificial Intelligence program aimed at addressing workforce demand for AI expertise, set to l...

AI News - General · 4 min ·
[2603.15159] To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation
Llms

[2603.15159] To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation

Abstract page for arXiv paper 2603.15159: To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation

arXiv - AI · 4 min ·
[2602.07374] TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Layer-wise Scaling
Llms

[2602.07374] TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Layer-wise Scaling

Abstract page for arXiv paper 2602.07374: TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Lay...

arXiv - AI · 4 min ·
[2512.11798] Particulate: Feed-Forward 3D Object Articulation
Machine Learning

[2512.11798] Particulate: Feed-Forward 3D Object Articulation

Abstract page for arXiv paper 2512.11798: Particulate: Feed-Forward 3D Object Articulation

arXiv - AI · 3 min ·
More in Ai Infrastructure: This Week Guide Trending

No comments

No comments yet. Be the first to comment!

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Daily or weekly digest • Unsubscribe anytime