Related papers: PASK: Toward Intent-Aware Proactive Agents with Lo…
As multi-agent LLM pipelines grow in complexity, existing serving paradigms fail to adapt to the dynamic serving conditions. We argue that agentic serving systems should be programmable and system-aware, unlike existing serving which…
Agentic artificial intelligence (AI) is an AI paradigm that can perceive the environment, reason over observations, and execute actions to achieve specific goals. Task-oriented communication supports agentic AI by transmitting only the…
Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…
The development of autonomous tool-use agents for complex, long-horizon tasks in collaboration with human users has become the frontier of agentic research. During multi-turn Human-AI interactions, the dynamic and uncertain nature of user…
Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…
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-latency…
Large Language Model (LLM)-based multi-agent systems (MAS) demonstrate remarkable potential for scientific discovery. Existing approaches, however, often automate scientific discovery using predefined workflows that lack rationality…
Despite the remarkable progress of large language models (LLMs), the capabilities of standalone LLMs have begun to plateau when tackling real-world, complex tasks that require interaction with external tools and dynamic environments.…
Space-air-ground integrated networks (SAGIN) promise ubiquitous 6G connectivity but face significant resource management challenges due to heterogeneous infrastructure, dynamic topologies, and stringent quality-of-service (QoS)…
The advent of always-on personal AI assistants, enabled by all-day wearable devices such as smart glasses, demands a new level of contextual understanding, one that goes beyond short, isolated events to encompass the continuous,…
With the advance of artificial intelligence (AI), the emergence of Google Gemini and OpenAI Q* marks the direction towards artificial general intelligence (AGI). To implement AGI, the concept of interactive AI (IAI) has been introduced,…
This paper presents a Spark-based modular LangGraph framework, designed to enhance machine learning workflows through scalability, visualization, and intelligent process optimization. At its core, the framework introduces Agent AI, a…
As 6G networks evolve into increasingly AI-driven, user-centric ecosystems, traditional reactive handover mechanisms demonstrate limitations, especially in mobile edge computing and autonomous agent-based service scenarios. This manuscript…
An intelligent agent operating in the real-world must balance achieving its goal with maintaining the safety and comfort of not only itself, but also other participants within the surrounding scene. This requires jointly reasoning about the…
With recent advances in Large Language Models (LLMs), Agentic AI has become phenomenal in real-world applications, moving toward multiple LLM-based agents to perceive, learn, reason, and act collaboratively. These LLM-based Multi-Agent…
Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) promise human-like interaction with software applications, yet long-horizon tasks remain challenging due to memory limitations. Existing approaches…
Large language models (LLMs) increasingly serve as the central control unit of AI agents, yet current approaches remain limited in their ability to deliver personalized interactions. While Retrieval Augmented Generation enhances LLM…
We study the problem of safe and intention-aware robot navigation in dense and interactive crowds. Most previous reinforcement learning (RL) based methods fail to consider different types of interactions among all agents or ignore the…
Large Language Models (LLMs) and other foundation models are increasingly used as the core of AI agents. In agentic workflows, these agents plan tasks, interact with humans and peers, and influence scientific outcomes across federated and…
A user can be represented as what he/she does along the history. A common way to deal with the user modeling problem is to manually extract all kinds of aggregated features over the heterogeneous behaviors, which may fail to fully represent…