Asynchronous Tool Usage for Real-Time Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909369177735168 |
|---|---|
| author | Ginart, Antonio A. Kodali, Naveen Lee, Jason Xiong, Caiming Savarese, Silvio Emmons, John |
| author_facet | Ginart, Antonio A. Kodali, Naveen Lee, Jason Xiong, Caiming Savarese, Silvio Emmons, John |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_21620 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Asynchronous Tool Usage for Real-Time Agents Ginart, Antonio A. Kodali, Naveen Lee, Jason Xiong, Caiming Savarese, Silvio Emmons, John Artificial Intelligence 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. |
| title | Asynchronous Tool Usage for Real-Time Agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2410.21620 |