Asynchronous Tool Usage for Real-Time Agents
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech Recognitionspeech-recognitionSpeech Recognitiontext-to-speechText to SpeechSimilar Papers 제목 키워드 기반
Speculative Interaction Agents: Building Real-Time Agents with Asynchronous I/O and Speculative Tool Calling
There is a growing demand for agentic AI technologies for a range of downstream applications like customer service and personal assistants. For applications where the agent needs to interact with a person, real-time low-…
Synthetic Data GenerationAsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios
Large language model (LLM)-based agents have shown strong capabilities in using external tools to solve complex tasks. However, existing evaluations often overlook the temporal dimension of tool use, especially the impac…
Evaluating Privilege Usage of Agents with Real-World Tools
Equipping LLM agents with real-world tools can substantially improve productivity. However, granting agents autonomy over tool use also transfers the associated privileges to both the agent and the underlying LLM. Improp…
Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning
Synchronizing decisions across multiple agents in realistic settings is problematic since it requires agents to wait for other agents to terminate and communicate about termination reliably. Ideally, agents should learn …
Decision MakingMulti-agent Reinforcement LearningPolicy Gradient Methodsreinforcement-learning+2AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agents
Embodied AI agents increasingly rely on large language models (LLMs) for planning, yet per-step LLM calls impose severe latency and cost. In this paper, we show that embodied tasks exhibit strong plan locality, where the…