Agentic CPU-GPU Scheduling for Heterogeneous AI Workloads

https://arxiv.org/abs/2607.22242v1

Core Idea

The problem is that existing frameworks assign all GPU-capable AI tools to the GPU by default, which is suboptimal for heterogeneous workloads.

For this daily profile, it is worth opening because it links LLM, Training, and GPU to a concrete method, not just a broad trend.

What Is New

The novelty signal is concentrated around LLM, Training, GPU, and Runtime. For this profile, the important question is whether the paper changes how architecture ideas are generated, evaluated, or connected to software and hardware constraints.

Methodology

Read this as a loop: define the target system, apply the proposed mechanism, measure against a baseline, then use the measured signal to justify the next design choice. Mechanism: Agentic AI systems compose heterogeneous tool workloads on shared GPU/CPU infrastructure, yet existing frameworks assign all GPU-capable tools to the GPU by default. Evidence: We profile 19 AI tools across GPU and CPU and find that 11 are GPU-preferred, 4 are ambiguous, 1 is CPU-preferred due to PCIe transfer dominance, and 3 are device-neutral, establishing that blanket GPU-first scheduling.

score(design) = quality_metric(design) - cost_to_evaluate(design) + feedback_gain(design)

Figure To Read First

Read this visual first: focus on the first architecture, workflow, or pipeline figure before the experiments. It should show what is optimized, what feedback signal is used, and where the system boundary sits.

Minimal Mental Model

research artifact
  question      -> what design, runtime, or system boundary changes?
  mechanism     -> model, agent, compiler, simulator, or hardware feedback
  evaluation    -> baseline comparison plus cost / latency / accuracy signal
  reusable idea -> what should carry into the next architecture experiment?

Why It Matters

Paper recommendations matter when they sharpen the research map: what problem is now easier to study, what methodology becomes reusable, and which architecture assumptions should be questioned next.