ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Bufang, Xu, Lilin, Zeng, Liekang, Liu, Kaiwei, Jiang, Siyang, Lu, Wenrui, Chen, Hongkai, Jiang, Xiaofan, Xing, Guoliang, Yan, Zhenyu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912671371100160
author Yang, Bufang
Xu, Lilin
Zeng, Liekang
Liu, Kaiwei
Jiang, Siyang
Lu, Wenrui
Chen, Hongkai
Jiang, Xiaofan
Xing, Guoliang
Yan, Zhenyu
author_facet Yang, Bufang
Xu, Lilin
Zeng, Liekang
Liu, Kaiwei
Jiang, Siyang
Lu, Wenrui
Chen, Hongkai
Jiang, Xiaofan
Xing, Guoliang
Yan, Zhenyu
contents Recent advances in Large Language Models (LLMs) have propelled intelligent agents from reactive responses to proactive support. While promising, existing proactive agents either rely exclusively on observations from enclosed environments (e.g., desktop UIs) with direct LLM inference or employ rule-based proactive notifications, leading to suboptimal user intent understanding and limited functionality for proactive service. In this paper, we introduce ContextAgent, the first context-aware proactive agent that incorporates extensive sensory contexts surrounding humans to enhance the proactivity of LLM agents. ContextAgent first extracts multi-dimensional contexts from massive sensory perceptions on wearables (e.g., video and audio) to understand user intentions. ContextAgent then leverages the sensory contexts and personas from historical data to predict the necessity for proactive services. When proactive assistance is needed, ContextAgent further automatically calls the necessary tools to assist users unobtrusively. To evaluate this new task, we curate ContextAgentBench, the first benchmark for evaluating context-aware proactive LLM agents, covering 1,000 samples across nine daily scenarios and twenty tools. Experiments on ContextAgentBench show that ContextAgent outperforms baselines by achieving up to 8.5% and 6.0% higher accuracy in proactive predictions and tool calling, respectively. We hope our research can inspire the development of more advanced, human-centric, proactive AI assistants. The code and dataset are publicly available at https://github.com/openaiotlab/ContextAgent.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14668
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions
Yang, Bufang
Xu, Lilin
Zeng, Liekang
Liu, Kaiwei
Jiang, Siyang
Lu, Wenrui
Chen, Hongkai
Jiang, Xiaofan
Xing, Guoliang
Yan, Zhenyu
Artificial Intelligence
Computation and Language
Human-Computer Interaction
Recent advances in Large Language Models (LLMs) have propelled intelligent agents from reactive responses to proactive support. While promising, existing proactive agents either rely exclusively on observations from enclosed environments (e.g., desktop UIs) with direct LLM inference or employ rule-based proactive notifications, leading to suboptimal user intent understanding and limited functionality for proactive service. In this paper, we introduce ContextAgent, the first context-aware proactive agent that incorporates extensive sensory contexts surrounding humans to enhance the proactivity of LLM agents. ContextAgent first extracts multi-dimensional contexts from massive sensory perceptions on wearables (e.g., video and audio) to understand user intentions. ContextAgent then leverages the sensory contexts and personas from historical data to predict the necessity for proactive services. When proactive assistance is needed, ContextAgent further automatically calls the necessary tools to assist users unobtrusively. To evaluate this new task, we curate ContextAgentBench, the first benchmark for evaluating context-aware proactive LLM agents, covering 1,000 samples across nine daily scenarios and twenty tools. Experiments on ContextAgentBench show that ContextAgent outperforms baselines by achieving up to 8.5% and 6.0% higher accuracy in proactive predictions and tool calling, respectively. We hope our research can inspire the development of more advanced, human-centric, proactive AI assistants. The code and dataset are publicly available at https://github.com/openaiotlab/ContextAgent.
title ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions
topic Artificial Intelligence
Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2505.14668