This paper introduces SwarmX, a system for scheduling agentic AI applications in GPU-CPU clusters using neural predictors, reducing tail latency by up to 61.5% and sustaining up to 2x the throughput o…

This paper identifies suboptimalities in default GPU-first scheduling for AI tool workloads and proposes an agentic scheduler that adaptively assigns tools to GPU or CPU based on runtime factors.

WAR is a workload-aware rollout system that accelerates synchronous agentic RL by optimizing decoding and scheduling strategies based on runtime load.

RACE-Sched is an asynchronous agentic framework that successfully integrates low-latency, real-time scheduling decisions with advanced, long-horizon reasoning provided by Large Language Models.

The paper proposes the concept of an Agent Operating System (AOS) to provide a necessary systems foundation for managing the unique, non-deterministic, and goal-directed execution characteristics of m…

The paper proposes the concept of an Agent Operating System (AOS) to provide a rigorous, controllable, and accountable systems foundation for running complex, probabilistic, and goal-directed AI agent…

The paper introduces HORIZON, a self-evolving agent framework for hardware design using git operations.

This paper proposes an organizational memory for LLM-based agents to access and share enterprise-specific procedural knowledge for reliable business process execution.

Agent libOS introduces a library-OS-inspired runtime substrate that treats LLM agents as schedulable processes, providing explicit capability control and robust auditing for long-running, stateful age…

The paper proposes a modular agent framework and novel learning methods to design and optimize practical, cost-effective, and controllable LLM-based agentic systems.

The paper presents a tool-making pipeline for production LLM agents that compiles repeated steps into validated, versioned tools before deployment, reducing latency and error rate.

MemPro introduces a system-level evolution framework that treats the entire memory construction-retrieval pipeline as an evolvable program, significantly improving long-horizon agent performance over…

The paper proposes Multi-Agent Computer Use (MACU) systems, which significantly improve performance on complex, long-horizon tasks by enabling parallel execution and dynamic task decomposition compare…

Leyline introduces a novel serving-side primitive that allows agentic LLMs to perform targeted, efficient edits to the KV cache, avoiding costly full re-prefilling after content modification.

MOSAIC is a novel scheduling framework that significantly accelerates Mixture-of-Agents (MoA) workloads by jointly optimizing expert placement and utilizing confidence-aware adaptive aggregation.

The paper presents Dyserve, a workflow-aware serving layer for agentic AI applications that compiles per-node model and verifier choices into an integer linear program, allowing for efficient model se…

The paper introduces GAIATrace, a comprehensive token-level dataset, and Vidur-Agent, a simulator, to enable reproducible and detailed system-level characterization of complex multi-model agentic AI s…

This paper introduces Retriever, an asynchronous decision model and runtime system for building long-horizon robot agents with explicit clock and input-consumption semantics.