# Hierarchical Server Architecture for Agentic Science

arXiv: https://arxiv.org/abs/2608.05332 · HTML: https://mlsanity.com/paper/2608.05332/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 2 of its 35 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 2 of 2)

- [Usability Evaluation of Cloud for HPC Applications](https://mlsanity.com/paper/2506.02709/) (2025)
- [Multi-Agent Collaboration for Automated Design Exploration on High Performance Computing Systems](https://mlsanity.com/paper/2603.11515/) (2026)

## Built on by (most cited first, 1 of 1)

- [ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations](https://mlsanity.com/paper/2609.32868/) (2026)

## Abstract (arXiv)

Agentic science is transforming the landscape of computational work, and is applied to scientific pipelines and workload managers. Scientific workloads require specialized hardware within and between institutions. Automated resource discovery is an essential step for scheduling workloads with specific hardware and environmental requirements. In this paper, we present a hierarchical, dynamic architecture and accompanying software to discover resources across diverse cloud, edge, and HPC systems. The design enables concurrent, asynchronous negotiation, selection, and dispatch of requests for work using secretary agents. The agents probe and discover 51 real and simulated providers across 7 categories. We perform 19,973 negotiation and 6,952 selection simulations to assess reliability of decisions, demonstrating high (87.71%) negotiation accuracy and selection costs comparable to more traditional strategies. Designed for extensibility and currently supporting the US DOE Genesis Mission, this architecture exemplifies the importance of careful coordination between agents, discovery tools, and infrastructure for agentic science.