Salvato in:
Dettagli Bibliografici
Autori principali: Gao, Hengjian, Zhang, Kaiwei, Wang, Shibo, Chen, Mingjie, Cao, Qihang, Wang, Xianfeng, Zhu, Yucheng, Min, Xiongkuo, Sun, Wei, Zhu, Dandan, Zhai, Guangtao
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.00490
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917300673708032
author Gao, Hengjian
Zhang, Kaiwei
Wang, Shibo
Chen, Mingjie
Cao, Qihang
Wang, Xianfeng
Zhu, Yucheng
Min, Xiongkuo
Sun, Wei
Zhu, Dandan
Zhai, Guangtao
author_facet Gao, Hengjian
Zhang, Kaiwei
Wang, Shibo
Chen, Mingjie
Cao, Qihang
Wang, Xianfeng
Zhu, Yucheng
Min, Xiongkuo
Sun, Wei
Zhu, Dandan
Zhai, Guangtao
contents The rapid progress of Multimodal Large Language Models (MLLMs) marks a significant step toward artificial general intelligence, offering great potential for augmenting human capabilities. However, their ability to provide effective assistance in dynamic, real-world environments remains largely underexplored. Existing video benchmarks predominantly assess passive understanding through retrospective analysis or isolated perception tasks, failing to capture the interactive and adaptive nature of real-time user assistance. To bridge this gap, we introduce LifeEval, a multimodal benchmark designed to evaluate real-time, task-oriented human-AI collaboration in daily life from an egocentric perspective. LifeEval emphasizes three key aspects: task-oriented holistic evaluation, egocentric real-time perception from continuous first-person streams, and human-assistant collaborative interaction through natural dialogues. Constructed via a rigorous annotation pipeline, the benchmark comprises 4,075 high-quality question-answer pairs across 6 core capability dimensions. Extensive evaluations of 26 state-of-the-art MLLMs on LifeEval reveal substantial challenges in achieving timely, effective and adaptive interaction, highlighting essential directions for advancing human-centered interactive intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00490
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LifeEval: A Multimodal Benchmark for Assistive AI in Egocentric Daily Life Tasks
Gao, Hengjian
Zhang, Kaiwei
Wang, Shibo
Chen, Mingjie
Cao, Qihang
Wang, Xianfeng
Zhu, Yucheng
Min, Xiongkuo
Sun, Wei
Zhu, Dandan
Zhai, Guangtao
Artificial Intelligence
The rapid progress of Multimodal Large Language Models (MLLMs) marks a significant step toward artificial general intelligence, offering great potential for augmenting human capabilities. However, their ability to provide effective assistance in dynamic, real-world environments remains largely underexplored. Existing video benchmarks predominantly assess passive understanding through retrospective analysis or isolated perception tasks, failing to capture the interactive and adaptive nature of real-time user assistance. To bridge this gap, we introduce LifeEval, a multimodal benchmark designed to evaluate real-time, task-oriented human-AI collaboration in daily life from an egocentric perspective. LifeEval emphasizes three key aspects: task-oriented holistic evaluation, egocentric real-time perception from continuous first-person streams, and human-assistant collaborative interaction through natural dialogues. Constructed via a rigorous annotation pipeline, the benchmark comprises 4,075 high-quality question-answer pairs across 6 core capability dimensions. Extensive evaluations of 26 state-of-the-art MLLMs on LifeEval reveal substantial challenges in achieving timely, effective and adaptive interaction, highlighting essential directions for advancing human-centered interactive intelligence.
title LifeEval: A Multimodal Benchmark for Assistive AI in Egocentric Daily Life Tasks
topic Artificial Intelligence
url https://arxiv.org/abs/2603.00490