Bookmark Saya

Semantic Scholar Open Access 2024 9 sitasi

Asynchronous Tool Usage for Real-Time Agents

Antonio A. Ginart Naveen Kodali Jason Lee Caiming Xiong Silvio Savarese +1 lainnya
Lihat Sumber DOI

Abstrak

While frontier large language models (LLMs) are capable tool-using agents, current AI systems still operate in a strict turn-based fashion, oblivious to passage of time. This synchronous design forces user queries and tool-use to occur sequentially, preventing the systems from multitasking and reducing interactivity. To address this limitation, we introduce asynchronous AI agents capable of parallel processing and real-time tool-use. Our key contribution is an event-driven finite-state machine architecture for agent execution and prompting, integrated with automatic speech recognition and text-to-speech. Drawing inspiration from the concepts originally developed for real-time operating systems, this work presents both a conceptual framework and practical tools for creating AI agents capable of fluid, multitasking interactions.

Topik & Kata Kunci

Computer Science

Penulis (6)

A

Antonio A. Ginart

N

Naveen Kodali

J

Jason Lee

C

Caiming Xiong

S

Silvio Savarese

J

John Emmons

Format Sitasi

APA MLA BibTeX
Ginart, A.A., Kodali, N., Lee, J., Xiong, C., Savarese, S., Emmons, J. (2024). Asynchronous Tool Usage for Real-Time Agents. https://doi.org/10.48550/arXiv.2410.21620

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber doi.org/10.48550/arXiv.2410.21620
Informasi Jurnal
Tahun Terbit
2024
Bahasa
en
Total Sitasi
9×
Sumber Database
Semantic Scholar
DOI
10.48550/arXiv.2410.21620
Akses
Open Access ✓