Related papers: A Policy-Driven Runtime Layer for Agentic LLM Serv…

Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…

The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…

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 next plan is…

In this work, we identify and address the core challenges of agentic memory management in LLM serving, where large-scale storage, frequent updates, and multiple coexisting agents jointly introduce complex and high-cost approximate nearest…

Agentic AI systems introduce a security surface that is qualitatively different from that of stateless LLMs. They persist memory, invoke external tools, coordinate with peer agents, and operate across sessions, allowing attacks to emerge…

The growing demand on high-quality and low-latency multimedia services has led to much interest in edge caching techniques. Motivated by this, we in this paper consider edge caching at the base stations with unknown content popularity…

Large Language Models (LLMs) are increasingly deployed in complex multi-agent applications that rely on external function calls. This workload creates severe performance challenges for the KV Cache: spatial contention leads to the eviction…

Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that are poorly understood. We study when end-to-end RL training…

This letter proposes a novel three-tier content caching architecture for Vehicular Fog Caching (VFC)-assisted platoon, where the VFC is formed by the vehicles driving near the platoon. The system strategically coordinates storage across…

Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties, yet their implications for agentic multi-step decision making remain underexplored. We…

We stress test monitoring systems for detecting covert misbehavior in autonomous LLM agents (e.g., secretly sharing private information). To this end, we systematize a monitor red teaming (MRT) workflow that incorporates: (1) varying levels…

We present Thinking While Driving, a concurrent routing framework that integrates LLMs into a graph-based traffic environment. Unlike approaches that require agents to stop and deliberate, our system enables LLM-based route planning while…

For years, we have built LLM serving systems like any other critical infrastructure: a single general-purpose stack, hand-tuned over many engineer-years, meant to support every model and workload. In this paper, we take the opposite bet: a…

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…

LLM-based user agents, which simulate user interaction behavior, are emerging as a promising approach to enhancing recommender systems. In real-world scenarios, users' interactions often exhibit cross-domain characteristics and are…

High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…

As large language models (LLMs) are increasingly deployed as autonomous agents, understanding how strategic behavior emerges in multi-agent environments has become an important alignment challenge. We take a neutral empirical stance and…

LLM-based multi-agent simulations are increasingly adopted across application domains, but remain difficult to scale due to GPU memory pressure. Each agent maintains private GPU-resident states, including models, prefix caches, and…

KV cache management is essential for efficient LLM inference. To maximize utilization, existing inference engines evict finished requests' KV cache if new requests are waiting. This policy breaks for agentic workloads, which interleave LLM…