Related papers: A Token/KV-Cache Communication Media Selection and…
In this paper, a semantic communication framework for image transmission is developed. In the investigated framework, a set of servers cooperatively transmit images to a set of users utilizing semantic communication techniques. To evaluate…
The growing demand for on-device large language model (LLM) inference highlights the need for efficient mobile edge computing (MEC) solutions, especially in resource-constrained settings. Speculative decoding offers a promising solution by…
With the emergence of large model-based agents, widely adopted transformer-based architectures inevitably produce excessively long token embeddings for transmission, which may result in high bandwidth overhead, increased power consumption…
Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with…
Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipelines, or task decompositions assigned a priori. In…
This paper proposes networked dynamics to solve resource allocation problems over time-varying multi-agent networks. The state of each agent represents the amount of used resources (or produced utilities) while the total amount of resources…
Token Communications (TokenCom) has recently emerged as an effective new paradigm, where tokens are the unified units of multimodal communications and computations, enabling efficient digital semantic- and goal-oriented communications in…
Semantic communication has gained attention as a key enabler for intelligent and context-aware communication. However, one of the key challenges of semantic communications is the need to tailor the resource allocation to meet the specific…
Multi-agent LLM systems routinely generate multiple candidate responses that are aggregated by an LLM judge. To reduce the dominant prefill cost in such pipelines, recent work advocates KV cache reuse across partially shared contexts and…
Heterogeneous network (HetNet) is a key enabler to largely boost network coverage and capacity in the forthcoming fifth-generation (5G) and beyond. To support the explosively growing mobile data volumes, wireless communications with…
Autoregressive Transformers rely on Key-Value (KV) caching to accelerate inference. However, the linear growth of the KV cache with context length leads to excessive memory consumption and bandwidth constraints. This bottleneck is…
Optimizing the communication structure of large language model based multi-agent systems (LLM-MAS) has been shown to improve downstream performance and reduce token usage. Existing methods typically rely on randomly sampled training tasks.…
Ramp merging is one of the bottlenecks in traffic systems, which commonly cause traffic congestion, accidents, and severe carbon emissions. In order to address this essential issue and enhance the safety and efficiency of connected and…
Large Language Models (LLMs) have revolutionized a wide range of domains such as natural language processing, computer vision, and multi-modal tasks due to their ability to comprehend context and perform logical reasoning. However, the…
Information exchange in multi-agent systems improves the cooperation among agents, especially in partially observable settings. In the real world, communication is often carried out over imperfect channels. This requires agents to handle…
The ubiquitous computing resources in 6G networks provide ideal environments for the fusion of large language models (LLMs) and intelligent services through the agent framework. With auxiliary modules and planning cores, LLM-enabled agents…
In this paper, we study the resource allocation problem for a cooperative device-to-device (D2D)-enabled wireless caching network, where each user randomly caches popular contents to its memory and shares the contents with nearby users…
6G will connect heterogeneous intelligent agents to make them operate complex cooperative tasks. When connecting intelligence, two main research questions arise to identify how AI and ML models behave depending on: i) their input data…
The possibility of jointly optimizing location sensing and communication resources, facilitated by the existence of communication and sensing spectrum sharing, is what promotes the system performance to a higher level. However, the rapid…
While traditional optimization and scheduling schemes are designed to meet fixed, predefined system requirements, future systems are moving toward user-driven approaches and personalized services, aiming to achieve high…