Story

arxiv_cs_ai ยท Apr 16, 2026 ยท paper

Source brief

Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines

arxiv.orgApr 16, 2026
original source linked

In brief

Agentic workflows carry out complex tasks by orchestrating multiple large language models (LLMs) and tools. Serving such workflows at a target throughput with low latency is challenging because they can be defined usi...

Continue reading

Read the original at arxiv.org โ†’Open in live feed