mlsanityData to 14 Oct 2026

Cortex: Workflow-Aware Resource Pooling and Scheduling for Agentic Serving

arXiv 2510.14126 ↗First posted 15 Oct 2025cs.DCcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce Cortex, a prototype workflow-aware serving platform designed for agentic workloads. The core principle of Cortex is stage isolation: it provisions dedicated resource pools for each distinct stage of an agentic workflow. This simple yet powerful strategy mitigates inter-stage interference in compute and memory, leading to better KV cache utilization, higher throughput, and more predictable performance. By customizing resource allocation and scheduling within each distinct stage of agentic workflows, Cortex lays the groundwork for more advanced, agent-native serving paradigms, including malleable resource management, speculative execution of workflow branches, and a shared, multi-tiered cache for "agentic state."

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). First posted on arXiv 15 Oct 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

Similar, not cited

Close in wording, no citation either way

  1. 2025Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms
  2. 2026Pythia: Exploiting Workflow Predictability for Efficient Agent-Native LLM Serving
  3. 2026[AAFLOW+] Stateful Operator Abstraction with Zero-Copy Distributed KV Cache Orchestration for Multi-Agent Workflows
  4. 2026Architectural Implications of Agentic AI Workflows
  5. 2026Serving Agentic Workflows with a Physical-Plan Compiler and Adaptive Runtime
  6. 2026Diamond Agent: Agentic Control of Federated HPC Resources as a Service
  7. 2026Workload-Aware Caching for Multi-Agent Systems
  8. 2026SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters