AI RESEARCH
MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems
arXiv CS.LG
•
ArXi:2604.26963v1 Announce Type: cross Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators. Agentic workloads induce a temporal shift from single-turn inference to multi-turn LLM-tool loops, and a spatial shift from chat-scale, GPU-only execution to repository-scale, GPU-CPU co-located execution. Consequently, coordinating heterogeneous resource demands of agentic execution has emerged as a critical system challenge.